├── README.md ├── dataset ├── data_for_eval │ ├── basic │ │ ├── llmbar │ │ │ ├── llmbar_test_1.csv │ │ │ ├── llmbar_test_10.csv │ │ │ ├── llmbar_test_2.csv │ │ │ ├── llmbar_test_3.csv │ │ │ ├── llmbar_test_4.csv │ │ │ ├── llmbar_test_5.csv │ │ │ ├── llmbar_test_6.csv │ │ │ ├── llmbar_test_7.csv │ │ │ ├── llmbar_test_8.csv │ │ │ └── llmbar_test_9.csv │ │ └── mtbench │ │ │ ├── mtbench_test_1.csv │ │ │ ├── mtbench_test_10.csv │ │ │ ├── mtbench_test_2.csv │ │ │ ├── mtbench_test_3.csv │ │ │ ├── mtbench_test_4.csv │ │ │ ├── mtbench_test_5.csv │ │ │ ├── mtbench_test_6.csv │ │ │ ├── mtbench_test_7.csv │ │ │ ├── mtbench_test_8.csv │ │ │ └── mtbench_test_9.csv │ └── case_study │ │ ├── metatool │ │ ├── metatool_1_3s.json │ │ ├── metatool_1_4s.json │ │ ├── metatool_1_5s.json │ │ ├── metatool_2_3s.json │ │ ├── metatool_2_4s.json │ │ ├── metatool_2_5s.json │ │ ├── metatool_3_3s.json │ │ ├── metatool_3_4s.json │ │ ├── metatool_3_5s.json │ │ ├── metatool_4_3s.json │ │ ├── metatool_4_4s.json │ │ ├── metatool_4_5s.json │ │ ├── metatool_5_3s.json │ │ ├── metatool_5_4s.json │ │ └── metatool_5_5s.json │ │ ├── rlaif │ │ ├── rlaif_1_2s.json │ │ ├── rlaif_2_2s.json │ │ ├── rlaif_3_2s.json │ │ ├── rlaif_4_2s.json │ │ └── rlaif_5_2s.json │ │ └── search │ │ ├── search_1_3s.json │ │ ├── search_1_4s.json │ │ ├── search_1_5s.json │ │ ├── search_2_3s.json │ │ ├── search_2_4s.json │ │ ├── search_2_5s.json │ │ ├── search_3_3s.json │ │ ├── search_3_4s.json │ │ ├── search_3_5s.json │ │ ├── search_4_3s.json │ │ ├── search_4_4s.json │ │ ├── search_4_5s.json │ │ ├── search_5_3s.json │ │ ├── search_5_4s.json │ │ └── search_5_5s.json ├── data_for_train │ └── basic │ │ ├── llmbar │ │ ├── llmbar_train_1.csv │ │ ├── llmbar_train_10.csv │ │ ├── llmbar_train_2.csv │ │ ├── llmbar_train_3.csv │ │ ├── llmbar_train_4.csv │ │ ├── llmbar_train_5.csv │ │ ├── llmbar_train_6.csv │ │ ├── llmbar_train_7.csv │ │ ├── llmbar_train_8.csv │ │ └── llmbar_train_9.csv │ │ └── mtbench │ │ ├── mtbench_train_1.csv │ │ ├── mtbench_train_10.csv │ │ ├── mtbench_train_2.csv │ │ ├── mtbench_train_3.csv │ │ ├── mtbench_train_4.csv │ │ ├── mtbench_train_5.csv │ │ ├── mtbench_train_6.csv │ │ ├── mtbench_train_7.csv │ │ ├── mtbench_train_8.csv │ │ └── mtbench_train_9.csv └── results_suffix │ ├── basic │ ├── llmbar.json │ └── mtbench.json │ └── case_study │ ├── metatool.json │ ├── rlaif.json │ └── search.json ├── experiments ├── basic_scripts │ ├── run_attack.sh │ └── run_eval.sh ├── case_study │ ├── case_study_prompt.py │ └── evaluate_casestudy.py ├── configs │ ├── llama2.py │ ├── llama3.py │ ├── mistral2.py │ ├── openchat35.py │ └── template.py ├── eval │ ├── llama2 │ │ ├── llama2_llmbar_1.json │ │ ├── llama2_llmbar_10.json │ │ ├── llama2_llmbar_2.json │ │ ├── llama2_llmbar_3.json │ │ ├── llama2_llmbar_4.json │ │ ├── llama2_llmbar_5.json │ │ ├── llama2_llmbar_6.json │ │ ├── llama2_llmbar_7.json │ │ ├── llama2_llmbar_8.json │ │ ├── llama2_llmbar_9.json │ │ ├── llama2_mtbench_1.json │ │ ├── llama2_mtbench_10.json │ │ ├── llama2_mtbench_2.json │ │ ├── llama2_mtbench_3.json │ │ ├── llama2_mtbench_4.json │ │ ├── llama2_mtbench_5.json │ │ ├── llama2_mtbench_6.json │ │ ├── llama2_mtbench_7.json │ │ ├── llama2_mtbench_8.json │ │ └── llama2_mtbench_9.json │ ├── llama3 │ │ ├── llama3_llmbar_1.json │ │ ├── llama3_llmbar_10.json │ │ ├── llama3_llmbar_2.json │ │ ├── llama3_llmbar_3.json │ │ ├── llama3_llmbar_4.json │ │ ├── llama3_llmbar_5.json │ │ ├── llama3_llmbar_6.json │ │ ├── llama3_llmbar_7.json │ │ ├── llama3_llmbar_8.json │ │ ├── llama3_llmbar_9.json │ │ ├── llama3_mtbench_1.json │ │ ├── llama3_mtbench_10.json │ │ ├── llama3_mtbench_2.json │ │ ├── llama3_mtbench_3.json │ │ ├── llama3_mtbench_4.json │ │ ├── llama3_mtbench_5.json │ │ ├── llama3_mtbench_6.json │ │ ├── llama3_mtbench_7.json │ │ ├── llama3_mtbench_8.json │ │ └── llama3_mtbench_9.json │ ├── mistral2 │ │ ├── mistral2_llmbar_1.json │ │ ├── mistral2_llmbar_10.json │ │ ├── mistral2_llmbar_2.json │ │ ├── mistral2_llmbar_3.json │ │ ├── mistral2_llmbar_4.json │ │ ├── mistral2_llmbar_5.json │ │ ├── mistral2_llmbar_6.json │ │ ├── mistral2_llmbar_7.json │ │ ├── mistral2_llmbar_8.json │ │ ├── mistral2_llmbar_9.json │ │ ├── mistral2_mtbench_1.json │ │ ├── mistral2_mtbench_10.json │ │ ├── mistral2_mtbench_2.json │ │ ├── mistral2_mtbench_3.json │ │ ├── mistral2_mtbench_4.json │ │ ├── mistral2_mtbench_5.json │ │ ├── mistral2_mtbench_6.json │ │ ├── mistral2_mtbench_7.json │ │ ├── mistral2_mtbench_8.json │ │ └── mistral2_mtbench_9.json │ └── openchat35 │ │ ├── openchat35_llmbar_1.json │ │ ├── openchat35_llmbar_10.json │ │ ├── openchat35_llmbar_2.json │ │ ├── openchat35_llmbar_3.json │ │ ├── openchat35_llmbar_4.json │ │ ├── openchat35_llmbar_5.json │ │ ├── openchat35_llmbar_6.json │ │ ├── openchat35_llmbar_7.json │ │ ├── openchat35_llmbar_8.json │ │ ├── openchat35_llmbar_9.json │ │ ├── openchat35_mtbench_1.json │ │ ├── openchat35_mtbench_10.json │ │ ├── openchat35_mtbench_2.json │ │ ├── openchat35_mtbench_3.json │ │ ├── openchat35_mtbench_4.json │ │ ├── openchat35_mtbench_5.json │ │ ├── openchat35_mtbench_6.json │ │ ├── openchat35_mtbench_7.json │ │ ├── openchat35_mtbench_8.json │ │ └── openchat35_mtbench_9.json ├── evaluate.py ├── main.py └── results │ ├── llama2 │ ├── llama2_llmbar_1.json │ ├── llama2_llmbar_10.json │ ├── llama2_llmbar_2.json │ ├── llama2_llmbar_3.json │ ├── llama2_llmbar_4.json │ ├── llama2_llmbar_5.json │ ├── llama2_llmbar_6.json │ ├── llama2_llmbar_7.json │ ├── llama2_llmbar_8.json │ ├── llama2_llmbar_9.json │ ├── llama2_mtbench_1.json │ ├── llama2_mtbench_10.json │ ├── llama2_mtbench_2.json │ ├── llama2_mtbench_3.json │ ├── llama2_mtbench_4.json │ ├── llama2_mtbench_5.json │ ├── llama2_mtbench_6.json │ ├── llama2_mtbench_7.json │ ├── llama2_mtbench_8.json │ └── llama2_mtbench_9.json │ ├── llama3 │ ├── llama3_llmbar_1.json │ ├── llama3_llmbar_10.json │ ├── llama3_llmbar_2.json │ ├── llama3_llmbar_3.json │ ├── llama3_llmbar_4.json │ ├── llama3_llmbar_5.json │ ├── llama3_llmbar_6.json │ ├── llama3_llmbar_7.json │ ├── llama3_llmbar_8.json │ ├── llama3_llmbar_9.json │ ├── llama3_mtbench_1.json │ ├── llama3_mtbench_10.json │ ├── llama3_mtbench_2.json │ ├── llama3_mtbench_3.json │ ├── llama3_mtbench_4.json │ ├── llama3_mtbench_5.json │ ├── llama3_mtbench_6.json │ ├── llama3_mtbench_7.json │ ├── llama3_mtbench_8.json │ └── llama3_mtbench_9.json │ ├── mistral2 │ ├── mistral2_llmbar_1.json │ ├── mistral2_llmbar_10.json │ ├── mistral2_llmbar_2.json │ ├── mistral2_llmbar_3.json │ ├── mistral2_llmbar_4.json │ ├── mistral2_llmbar_5.json │ ├── mistral2_llmbar_6.json │ ├── mistral2_llmbar_7.json │ ├── mistral2_llmbar_8.json │ ├── mistral2_llmbar_9.json │ ├── mistral2_mtbench_1.json │ ├── mistral2_mtbench_10.json │ ├── mistral2_mtbench_2.json │ ├── mistral2_mtbench_3.json │ ├── mistral2_mtbench_4.json │ ├── mistral2_mtbench_5.json │ ├── mistral2_mtbench_6.json │ ├── mistral2_mtbench_7.json │ ├── mistral2_mtbench_8.json │ └── mistral2_mtbench_9.json │ └── openchat35 │ ├── openchat35_llmbar_1.json │ ├── openchat35_llmbar_10.json │ ├── openchat35_llmbar_2.json │ ├── openchat35_llmbar_3.json │ ├── openchat35_llmbar_4.json │ ├── openchat35_llmbar_5.json │ ├── openchat35_llmbar_6.json │ ├── openchat35_llmbar_7.json │ ├── openchat35_llmbar_8.json │ ├── openchat35_llmbar_9.json │ ├── openchat35_mtbench_1.json │ ├── openchat35_mtbench_10.json │ ├── openchat35_mtbench_2.json │ ├── openchat35_mtbench_3.json │ ├── openchat35_mtbench_4.json │ ├── openchat35_mtbench_5.json │ ├── openchat35_mtbench_6.json │ ├── openchat35_mtbench_7.json │ ├── openchat35_mtbench_8.json │ └── openchat35_mtbench_9.json ├── image └── main_example.png ├── judge_attack ├── __init__.py ├── base │ └── attack_manager.py └── gcg │ ├── __init__.py │ └── gcg_attack.py ├── requirements.txt └── setup.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/README.md -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/llmbar/llmbar_test_1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/llmbar/llmbar_test_1.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/llmbar/llmbar_test_10.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/llmbar/llmbar_test_10.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/llmbar/llmbar_test_2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/llmbar/llmbar_test_2.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/llmbar/llmbar_test_3.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/llmbar/llmbar_test_3.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/llmbar/llmbar_test_4.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/llmbar/llmbar_test_4.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/llmbar/llmbar_test_5.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/llmbar/llmbar_test_5.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/llmbar/llmbar_test_6.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/llmbar/llmbar_test_6.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/llmbar/llmbar_test_7.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/llmbar/llmbar_test_7.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/llmbar/llmbar_test_8.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/llmbar/llmbar_test_8.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/llmbar/llmbar_test_9.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/llmbar/llmbar_test_9.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/mtbench/mtbench_test_1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/mtbench/mtbench_test_1.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/mtbench/mtbench_test_10.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/mtbench/mtbench_test_10.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/mtbench/mtbench_test_2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/mtbench/mtbench_test_2.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/mtbench/mtbench_test_3.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/mtbench/mtbench_test_3.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/mtbench/mtbench_test_4.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/mtbench/mtbench_test_4.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/mtbench/mtbench_test_5.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/mtbench/mtbench_test_5.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/mtbench/mtbench_test_6.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/mtbench/mtbench_test_6.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/mtbench/mtbench_test_7.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/mtbench/mtbench_test_7.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/mtbench/mtbench_test_8.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/mtbench/mtbench_test_8.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/basic/mtbench/mtbench_test_9.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/basic/mtbench/mtbench_test_9.csv -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/metatool/metatool_1_3s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/metatool/metatool_1_3s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/metatool/metatool_1_4s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/metatool/metatool_1_4s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/metatool/metatool_1_5s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/metatool/metatool_1_5s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/metatool/metatool_2_3s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/metatool/metatool_2_3s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/metatool/metatool_2_4s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/metatool/metatool_2_4s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/metatool/metatool_2_5s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/metatool/metatool_2_5s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/metatool/metatool_3_3s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/metatool/metatool_3_3s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/metatool/metatool_3_4s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/metatool/metatool_3_4s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/metatool/metatool_3_5s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/metatool/metatool_3_5s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/metatool/metatool_4_3s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/metatool/metatool_4_3s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/metatool/metatool_4_4s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/metatool/metatool_4_4s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/metatool/metatool_4_5s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/metatool/metatool_4_5s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/metatool/metatool_5_3s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/metatool/metatool_5_3s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/metatool/metatool_5_4s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/metatool/metatool_5_4s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/metatool/metatool_5_5s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/metatool/metatool_5_5s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/rlaif/rlaif_1_2s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/rlaif/rlaif_1_2s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/rlaif/rlaif_2_2s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/rlaif/rlaif_2_2s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/rlaif/rlaif_3_2s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/rlaif/rlaif_3_2s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/rlaif/rlaif_4_2s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/rlaif/rlaif_4_2s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/rlaif/rlaif_5_2s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/rlaif/rlaif_5_2s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/search/search_1_3s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/search/search_1_3s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/search/search_1_4s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/search/search_1_4s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/search/search_1_5s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/search/search_1_5s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/search/search_2_3s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/search/search_2_3s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/search/search_2_4s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/search/search_2_4s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/search/search_2_5s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/search/search_2_5s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/search/search_3_3s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/search/search_3_3s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/search/search_3_4s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/search/search_3_4s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/search/search_3_5s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/search/search_3_5s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/search/search_4_3s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/search/search_4_3s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/search/search_4_4s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/search/search_4_4s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/search/search_4_5s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/search/search_4_5s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/search/search_5_3s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/search/search_5_3s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/search/search_5_4s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/search/search_5_4s.json -------------------------------------------------------------------------------- /dataset/data_for_eval/case_study/search/search_5_5s.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_eval/case_study/search/search_5_5s.json -------------------------------------------------------------------------------- /dataset/data_for_train/basic/llmbar/llmbar_train_1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/llmbar/llmbar_train_1.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/llmbar/llmbar_train_10.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/llmbar/llmbar_train_10.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/llmbar/llmbar_train_2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/llmbar/llmbar_train_2.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/llmbar/llmbar_train_3.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/llmbar/llmbar_train_3.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/llmbar/llmbar_train_4.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/llmbar/llmbar_train_4.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/llmbar/llmbar_train_5.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/llmbar/llmbar_train_5.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/llmbar/llmbar_train_6.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/llmbar/llmbar_train_6.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/llmbar/llmbar_train_7.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/llmbar/llmbar_train_7.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/llmbar/llmbar_train_8.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/llmbar/llmbar_train_8.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/llmbar/llmbar_train_9.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/llmbar/llmbar_train_9.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/mtbench/mtbench_train_1.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/mtbench/mtbench_train_1.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/mtbench/mtbench_train_10.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/mtbench/mtbench_train_10.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/mtbench/mtbench_train_2.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/mtbench/mtbench_train_2.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/mtbench/mtbench_train_3.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/mtbench/mtbench_train_3.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/mtbench/mtbench_train_4.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/mtbench/mtbench_train_4.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/mtbench/mtbench_train_5.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/mtbench/mtbench_train_5.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/mtbench/mtbench_train_6.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/mtbench/mtbench_train_6.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/mtbench/mtbench_train_7.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/mtbench/mtbench_train_7.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/mtbench/mtbench_train_8.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/mtbench/mtbench_train_8.csv -------------------------------------------------------------------------------- /dataset/data_for_train/basic/mtbench/mtbench_train_9.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/data_for_train/basic/mtbench/mtbench_train_9.csv -------------------------------------------------------------------------------- /dataset/results_suffix/basic/llmbar.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/results_suffix/basic/llmbar.json -------------------------------------------------------------------------------- /dataset/results_suffix/basic/mtbench.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/results_suffix/basic/mtbench.json -------------------------------------------------------------------------------- /dataset/results_suffix/case_study/metatool.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/results_suffix/case_study/metatool.json -------------------------------------------------------------------------------- /dataset/results_suffix/case_study/rlaif.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/results_suffix/case_study/rlaif.json -------------------------------------------------------------------------------- /dataset/results_suffix/case_study/search.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/dataset/results_suffix/case_study/search.json -------------------------------------------------------------------------------- /experiments/basic_scripts/run_attack.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/basic_scripts/run_attack.sh -------------------------------------------------------------------------------- /experiments/basic_scripts/run_eval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/basic_scripts/run_eval.sh -------------------------------------------------------------------------------- /experiments/case_study/case_study_prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/case_study/case_study_prompt.py -------------------------------------------------------------------------------- /experiments/case_study/evaluate_casestudy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/case_study/evaluate_casestudy.py -------------------------------------------------------------------------------- /experiments/configs/llama2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/configs/llama2.py -------------------------------------------------------------------------------- /experiments/configs/llama3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/configs/llama3.py -------------------------------------------------------------------------------- /experiments/configs/mistral2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/configs/mistral2.py -------------------------------------------------------------------------------- /experiments/configs/openchat35.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/configs/openchat35.py -------------------------------------------------------------------------------- /experiments/configs/template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/configs/template.py -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_llmbar_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_llmbar_1.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_llmbar_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_llmbar_10.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_llmbar_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_llmbar_2.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_llmbar_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_llmbar_3.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_llmbar_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_llmbar_4.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_llmbar_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_llmbar_5.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_llmbar_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_llmbar_6.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_llmbar_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_llmbar_7.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_llmbar_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_llmbar_8.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_llmbar_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_llmbar_9.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_mtbench_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_mtbench_1.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_mtbench_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_mtbench_10.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_mtbench_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_mtbench_2.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_mtbench_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_mtbench_3.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_mtbench_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_mtbench_4.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_mtbench_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_mtbench_5.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_mtbench_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_mtbench_6.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_mtbench_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_mtbench_7.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_mtbench_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_mtbench_8.json -------------------------------------------------------------------------------- /experiments/eval/llama2/llama2_mtbench_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama2/llama2_mtbench_9.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_llmbar_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_llmbar_1.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_llmbar_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_llmbar_10.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_llmbar_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_llmbar_2.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_llmbar_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_llmbar_3.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_llmbar_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_llmbar_4.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_llmbar_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_llmbar_5.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_llmbar_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_llmbar_6.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_llmbar_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_llmbar_7.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_llmbar_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_llmbar_8.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_llmbar_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_llmbar_9.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_mtbench_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_mtbench_1.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_mtbench_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_mtbench_10.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_mtbench_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_mtbench_2.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_mtbench_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_mtbench_3.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_mtbench_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_mtbench_4.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_mtbench_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_mtbench_5.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_mtbench_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_mtbench_6.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_mtbench_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_mtbench_7.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_mtbench_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_mtbench_8.json -------------------------------------------------------------------------------- /experiments/eval/llama3/llama3_mtbench_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/llama3/llama3_mtbench_9.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_llmbar_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_llmbar_1.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_llmbar_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_llmbar_10.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_llmbar_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_llmbar_2.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_llmbar_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_llmbar_3.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_llmbar_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_llmbar_4.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_llmbar_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_llmbar_5.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_llmbar_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_llmbar_6.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_llmbar_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_llmbar_7.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_llmbar_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_llmbar_8.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_llmbar_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_llmbar_9.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_mtbench_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_mtbench_1.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_mtbench_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_mtbench_10.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_mtbench_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_mtbench_2.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_mtbench_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_mtbench_3.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_mtbench_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_mtbench_4.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_mtbench_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_mtbench_5.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_mtbench_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_mtbench_6.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_mtbench_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_mtbench_7.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_mtbench_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_mtbench_8.json -------------------------------------------------------------------------------- /experiments/eval/mistral2/mistral2_mtbench_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/mistral2/mistral2_mtbench_9.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_llmbar_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_llmbar_1.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_llmbar_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_llmbar_10.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_llmbar_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_llmbar_2.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_llmbar_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_llmbar_3.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_llmbar_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_llmbar_4.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_llmbar_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_llmbar_5.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_llmbar_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_llmbar_6.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_llmbar_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_llmbar_7.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_llmbar_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_llmbar_8.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_llmbar_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_llmbar_9.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_mtbench_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_mtbench_1.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_mtbench_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_mtbench_10.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_mtbench_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_mtbench_2.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_mtbench_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_mtbench_3.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_mtbench_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_mtbench_4.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_mtbench_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_mtbench_5.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_mtbench_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_mtbench_6.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_mtbench_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_mtbench_7.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_mtbench_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_mtbench_8.json -------------------------------------------------------------------------------- /experiments/eval/openchat35/openchat35_mtbench_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/eval/openchat35/openchat35_mtbench_9.json -------------------------------------------------------------------------------- /experiments/evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/evaluate.py -------------------------------------------------------------------------------- /experiments/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/main.py -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_llmbar_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_llmbar_1.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_llmbar_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_llmbar_10.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_llmbar_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_llmbar_2.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_llmbar_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_llmbar_3.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_llmbar_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_llmbar_4.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_llmbar_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_llmbar_5.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_llmbar_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_llmbar_6.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_llmbar_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_llmbar_7.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_llmbar_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_llmbar_8.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_llmbar_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_llmbar_9.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_mtbench_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_mtbench_1.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_mtbench_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_mtbench_10.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_mtbench_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_mtbench_2.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_mtbench_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_mtbench_3.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_mtbench_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_mtbench_4.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_mtbench_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_mtbench_5.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_mtbench_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_mtbench_6.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_mtbench_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_mtbench_7.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_mtbench_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_mtbench_8.json -------------------------------------------------------------------------------- /experiments/results/llama2/llama2_mtbench_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama2/llama2_mtbench_9.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_llmbar_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_llmbar_1.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_llmbar_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_llmbar_10.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_llmbar_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_llmbar_2.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_llmbar_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_llmbar_3.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_llmbar_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_llmbar_4.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_llmbar_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_llmbar_5.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_llmbar_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_llmbar_6.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_llmbar_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_llmbar_7.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_llmbar_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_llmbar_8.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_llmbar_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_llmbar_9.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_mtbench_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_mtbench_1.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_mtbench_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_mtbench_10.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_mtbench_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_mtbench_2.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_mtbench_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_mtbench_3.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_mtbench_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_mtbench_4.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_mtbench_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_mtbench_5.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_mtbench_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_mtbench_6.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_mtbench_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_mtbench_7.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_mtbench_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_mtbench_8.json -------------------------------------------------------------------------------- /experiments/results/llama3/llama3_mtbench_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/llama3/llama3_mtbench_9.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_llmbar_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_llmbar_1.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_llmbar_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_llmbar_10.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_llmbar_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_llmbar_2.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_llmbar_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_llmbar_3.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_llmbar_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_llmbar_4.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_llmbar_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_llmbar_5.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_llmbar_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_llmbar_6.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_llmbar_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_llmbar_7.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_llmbar_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_llmbar_8.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_llmbar_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_llmbar_9.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_mtbench_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_mtbench_1.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_mtbench_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_mtbench_10.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_mtbench_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_mtbench_2.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_mtbench_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_mtbench_3.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_mtbench_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_mtbench_4.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_mtbench_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_mtbench_5.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_mtbench_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_mtbench_6.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_mtbench_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_mtbench_7.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_mtbench_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_mtbench_8.json -------------------------------------------------------------------------------- /experiments/results/mistral2/mistral2_mtbench_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/mistral2/mistral2_mtbench_9.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_llmbar_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_llmbar_1.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_llmbar_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_llmbar_10.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_llmbar_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_llmbar_2.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_llmbar_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_llmbar_3.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_llmbar_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_llmbar_4.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_llmbar_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_llmbar_5.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_llmbar_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_llmbar_6.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_llmbar_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_llmbar_7.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_llmbar_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_llmbar_8.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_llmbar_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_llmbar_9.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_mtbench_1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_mtbench_1.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_mtbench_10.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_mtbench_10.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_mtbench_2.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_mtbench_2.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_mtbench_3.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_mtbench_3.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_mtbench_4.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_mtbench_4.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_mtbench_5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_mtbench_5.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_mtbench_6.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_mtbench_6.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_mtbench_7.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_mtbench_7.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_mtbench_8.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_mtbench_8.json -------------------------------------------------------------------------------- /experiments/results/openchat35/openchat35_mtbench_9.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/experiments/results/openchat35/openchat35_mtbench_9.json -------------------------------------------------------------------------------- /image/main_example.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/image/main_example.png -------------------------------------------------------------------------------- /judge_attack/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/judge_attack/__init__.py -------------------------------------------------------------------------------- /judge_attack/base/attack_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/judge_attack/base/attack_manager.py -------------------------------------------------------------------------------- /judge_attack/gcg/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/judge_attack/gcg/__init__.py -------------------------------------------------------------------------------- /judge_attack/gcg/gcg_attack.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/judge_attack/gcg/gcg_attack.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | transformers==4.42.3 2 | ml_collections 3 | fschat>=0.2.36 4 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ShiJiawenwen/JudgeDeceiver/HEAD/setup.py --------------------------------------------------------------------------------