├── LICENSE ├── README.md ├── data ├── baseline │ ├── reference_corpus.json │ ├── reference_corpus_dream.json │ └── reference_corpus_llada.json ├── countdown.jsonl ├── gpqa.jsonl ├── gsm8k.jsonl ├── humaneval.jsonl ├── math500.jsonl ├── sanitized-mbpp.json └── sudoku.csv ├── figs ├── confidence.png ├── entropy.png ├── linear.png ├── margin.png └── pc_sampler.png ├── requirements.txt ├── results └── humaneval_results │ ├── 1.py │ ├── 2.py │ ├── 3.py │ ├── 4.py │ ├── 5.py │ ├── 6.py │ ├── 7.py │ ├── 8.py │ └── 9.py ├── scripts ├── eval.py ├── eval_eb_sampler.sh ├── eval_entropy.sh ├── eval_fast_dllm.sh ├── eval_linear_position.sh ├── eval_llada.py ├── eval_llada_remdm.py ├── eval_margin.sh ├── eval_pc_sampler.sh ├── eval_remdm.py ├── eval_remdm.sh ├── eval_semi_ar.sh ├── heatmap.sh ├── method_comparison_heatmap.py └── paint_heatmap.py ├── src ├── __pycache__ │ ├── generate.cpython-310.pyc │ ├── llama_template.cpython-310.pyc │ └── template.cpython-310.pyc ├── generate.py ├── llama_template.py └── template.py └── utils ├── __pycache__ ├── eval_utils.cpython-310.pyc └── load_json_or_jsonl.cpython-310.pyc ├── calculate_p_baseline.py ├── eval_utils.py ├── judge_python_code.py └── load_json_or_jsonl.py /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/README.md -------------------------------------------------------------------------------- /data/baseline/reference_corpus.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/data/baseline/reference_corpus.json -------------------------------------------------------------------------------- /data/baseline/reference_corpus_dream.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/data/baseline/reference_corpus_dream.json -------------------------------------------------------------------------------- /data/baseline/reference_corpus_llada.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/data/baseline/reference_corpus_llada.json -------------------------------------------------------------------------------- /data/countdown.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/data/countdown.jsonl -------------------------------------------------------------------------------- /data/gpqa.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/data/gpqa.jsonl -------------------------------------------------------------------------------- /data/gsm8k.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/data/gsm8k.jsonl -------------------------------------------------------------------------------- /data/humaneval.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/data/humaneval.jsonl -------------------------------------------------------------------------------- /data/math500.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/data/math500.jsonl -------------------------------------------------------------------------------- /data/sanitized-mbpp.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/data/sanitized-mbpp.json -------------------------------------------------------------------------------- /data/sudoku.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/data/sudoku.csv -------------------------------------------------------------------------------- /figs/confidence.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/figs/confidence.png -------------------------------------------------------------------------------- /figs/entropy.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/figs/entropy.png -------------------------------------------------------------------------------- /figs/linear.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/figs/linear.png -------------------------------------------------------------------------------- /figs/margin.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/figs/margin.png -------------------------------------------------------------------------------- /figs/pc_sampler.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/figs/pc_sampler.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/requirements.txt -------------------------------------------------------------------------------- /results/humaneval_results/1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/results/humaneval_results/1.py -------------------------------------------------------------------------------- /results/humaneval_results/2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/results/humaneval_results/2.py -------------------------------------------------------------------------------- /results/humaneval_results/3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/results/humaneval_results/3.py -------------------------------------------------------------------------------- /results/humaneval_results/4.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/results/humaneval_results/4.py -------------------------------------------------------------------------------- /results/humaneval_results/5.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/results/humaneval_results/5.py -------------------------------------------------------------------------------- /results/humaneval_results/6.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/results/humaneval_results/6.py -------------------------------------------------------------------------------- /results/humaneval_results/7.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/results/humaneval_results/7.py -------------------------------------------------------------------------------- /results/humaneval_results/8.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/results/humaneval_results/8.py -------------------------------------------------------------------------------- /results/humaneval_results/9.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/results/humaneval_results/9.py -------------------------------------------------------------------------------- /scripts/eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/scripts/eval.py -------------------------------------------------------------------------------- /scripts/eval_eb_sampler.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/scripts/eval_eb_sampler.sh -------------------------------------------------------------------------------- /scripts/eval_entropy.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/scripts/eval_entropy.sh -------------------------------------------------------------------------------- /scripts/eval_fast_dllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/scripts/eval_fast_dllm.sh -------------------------------------------------------------------------------- /scripts/eval_linear_position.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/scripts/eval_linear_position.sh -------------------------------------------------------------------------------- /scripts/eval_llada.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/scripts/eval_llada.py -------------------------------------------------------------------------------- /scripts/eval_llada_remdm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/scripts/eval_llada_remdm.py -------------------------------------------------------------------------------- /scripts/eval_margin.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/scripts/eval_margin.sh -------------------------------------------------------------------------------- /scripts/eval_pc_sampler.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/scripts/eval_pc_sampler.sh -------------------------------------------------------------------------------- /scripts/eval_remdm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/scripts/eval_remdm.py -------------------------------------------------------------------------------- /scripts/eval_remdm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/scripts/eval_remdm.sh -------------------------------------------------------------------------------- /scripts/eval_semi_ar.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/scripts/eval_semi_ar.sh -------------------------------------------------------------------------------- /scripts/heatmap.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/scripts/heatmap.sh -------------------------------------------------------------------------------- /scripts/method_comparison_heatmap.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/scripts/method_comparison_heatmap.py -------------------------------------------------------------------------------- /scripts/paint_heatmap.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/scripts/paint_heatmap.py -------------------------------------------------------------------------------- /src/__pycache__/generate.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/src/__pycache__/generate.cpython-310.pyc -------------------------------------------------------------------------------- /src/__pycache__/llama_template.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/src/__pycache__/llama_template.cpython-310.pyc -------------------------------------------------------------------------------- /src/__pycache__/template.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/src/__pycache__/template.cpython-310.pyc -------------------------------------------------------------------------------- /src/generate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/src/generate.py -------------------------------------------------------------------------------- /src/llama_template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/src/llama_template.py -------------------------------------------------------------------------------- /src/template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/src/template.py -------------------------------------------------------------------------------- /utils/__pycache__/eval_utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/utils/__pycache__/eval_utils.cpython-310.pyc -------------------------------------------------------------------------------- /utils/__pycache__/load_json_or_jsonl.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/utils/__pycache__/load_json_or_jsonl.cpython-310.pyc -------------------------------------------------------------------------------- /utils/calculate_p_baseline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/utils/calculate_p_baseline.py -------------------------------------------------------------------------------- /utils/eval_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/utils/eval_utils.py -------------------------------------------------------------------------------- /utils/judge_python_code.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/utils/judge_python_code.py -------------------------------------------------------------------------------- /utils/load_json_or_jsonl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NEUIR/PC-Sampler/HEAD/utils/load_json_or_jsonl.py --------------------------------------------------------------------------------