├── Applications.png ├── RAG_Applications.png ├── RAG_Enhancements.png ├── RAG_Foundations.png ├── RAG_Overview.jpg └── README.md /Applications.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hymie122/RAG-Survey/feb4dfa59ff8f9a8522fc8dfda77e4d6ea0fbe5f/Applications.png -------------------------------------------------------------------------------- /RAG_Applications.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hymie122/RAG-Survey/feb4dfa59ff8f9a8522fc8dfda77e4d6ea0fbe5f/RAG_Applications.png -------------------------------------------------------------------------------- /RAG_Enhancements.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hymie122/RAG-Survey/feb4dfa59ff8f9a8522fc8dfda77e4d6ea0fbe5f/RAG_Enhancements.png -------------------------------------------------------------------------------- /RAG_Foundations.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hymie122/RAG-Survey/feb4dfa59ff8f9a8522fc8dfda77e4d6ea0fbe5f/RAG_Foundations.png -------------------------------------------------------------------------------- /RAG_Overview.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hymie122/RAG-Survey/feb4dfa59ff8f9a8522fc8dfda77e4d6ea0fbe5f/RAG_Overview.jpg -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Retrieval-Augmented Generation for AI-Generated Content: A Survey 2 | This repo is constructed for collecting and categorizing papers about RAG according to our survey paper: [*Retrieval-Augmented Generation for AI-Generated Content: A Survey*](https://arxiv.org/abs/2402.19473). Considering the rapid growth of this field, we will continue to update both [paper](https://arxiv.org/abs/2402.19473) and this repo. 3 | 4 | # Overview 5 |
image 6 | 7 | # Catalogue 8 | ## Methods Taxonomy 9 | ### RAG Foundations 10 |
image 11 | 12 | - Query-based RAG 13 | 14 | [REALM: Retrieval-Augmented Language Model Pre-Training](https://arxiv.org/abs/2002.08909) 15 | 16 | [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://arxiv.org/abs/2310.11511) 17 | 18 | [REPLUG: Retrieval-Augmented Black-Box Language Models](https://arxiv.org/abs/2301.12652) 19 | 20 | [In-Context Retrieval-Augmented Language Models](https://arxiv.org/abs/2302.00083) 21 | 22 | [When Language Model Meets Private Library](https://arxiv.org/abs/2210.17236) 23 | 24 | [DocPrompting: Generating Code by Retrieving the Docs](https://openreview.net/pdf?id=ZTCxT2t2Ru) 25 | 26 | [Retrieval-based prompt selection for code-related few-shot learning](https://doi.org/10.1109/ICSE48619.2023.00205) 27 | 28 | [Inferfix: End-to-end program repair with llms](https://doi.org/10.1145/3611643.3613892) 29 | 30 | [Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models](https://proceedings.mlr.press/v202/huang23i.html) 31 | 32 | 33 | 34 | [Reacc: A retrieval-augmented code completion framework](https://doi.org/10.18653/v1/2022.acl-long.431) 35 | 36 | 37 | [Uni-parser: Unified semantic parser for question answering on knowledge base and database](https://doi.org/10.18653/v1/2022.emnlp-main.605) 38 | 39 | 40 | [RNG-KBQA: generation augmented iterative ranking for knowledge base question answering](https://doi.org/10.18653/v1/2022.acl-long.417) 41 | 42 | [End-to-end casebased reasoning for commonsense knowledge base completion](https://doi.org/10.18653/v1/2023.eacl-main.255) 43 | 44 | [Combining transfer learning with in-context learning using blackbox llms for zero-shot knowledge base question answering](https://doi.org/10.48550/arXiv.2311.08894) 45 | 46 | [Genegpt: Augmenting large language models with domain tools for improved access to biomedical information](https://arxiv.org/abs/2304.09667) 47 | 48 | [Retrieval-augmented large language models for adolescent idiopathic scoliosis patients in shared decision-making](https://dl.acm.org/doi/10.1145/3584371.3612956) 49 | 50 | [Retrievegan:Image synthesis via differentiable patch retrieval](https://link.springer.com/chapter/10.1007/978-3-030-58598-3_15) 51 | 52 | [Instance-conditioned gan](https://proceedings.neurips.cc/paper/2021/file/e7ac288b0f2d41445904d071ba37aaff-Paper.pdf) 53 | 54 | 55 | [Retrieval-Augmented Score Distillation for Text-to-3D Generation](https://doi.org/10.48550/arXiv.2402.02972) 56 | 57 | - Latent Representation-based RAG 58 | 59 | [Leveraging passage retrieval with generative models for open domain question answering](https://doi.org/10.18653/v1/2021.eacl-main.74) 60 | 61 | 62 | [Bashexplainer: Retrieval-augmented bash code comment generation based on finetuned codebert](https://doi.org/10.1109/ICSME55016.2022.00016) 63 | 64 | [EditSum: A Retrieve-and-Edit Framework for Source Code Summarization](https://doi.org/10.1109/ASE51524.2021.9678724) 65 | 66 | [Retrieve and Refine: Exemplar-based Neural Comment Generation](https://arxiv.org/abs/2010.04459) 67 | 68 | [RACE: retrieval-augmented commit message generation](https://doi.org/10.18653/v1/2022.emnlp-main.372) 69 | 70 | [Unik-qa: Unified representations of structured and unstructured knowledge for open-domain question answering](https://doi.org/10.18653/v1/2022.findings-naacl.115) 71 | 72 | [A Retrieve-and-Edit Framework for Predicting Structured Outputs](https://proceedings.neurips.cc/paper/2018/hash/cd17d3ce3b64f227987cd92cd701cc58-Abstract.html) 73 | 74 | 75 | 76 | [DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases](https://openreview.net/pdf?id=XHc5zRPxqV9) 77 | 78 | [Bridging the kb-text gap: Leveraging structured knowledge-aware pre-training for KBQA](https://doi.org/10.1145/3583780.3615150) 79 | 80 | [Knowledge-driven cot: Exploring faithful reasoning in llms for knowledge-intensive question answering](https://doi.org/10.48550/arXiv.2308.13259) 81 | 82 | [Retrieval-enhanced generative model for large-scale knowledge graph completion](https://doi.org/10.1145/3539618.3592052) 83 | 84 | [Case-based reasoning for natural language queries over knowledge bases](https://doi.org/10.18653/v1/2021) 85 | 86 | 87 | 88 | [A Protein-Ligand Interaction-focused 3D Molecular Generative Framework for Generalizable Structure-based Drug Design](https://chemrxiv.org/engage/chemrxiv/article-details/6482d9dbbe16ad5c57af1937) 89 | 90 | [Improving language models by retrieving from trillions of tokens](https://proceedings.mlr.press/v162/borgeaud22a.html) 91 | 92 | [Remodiffuse: Retrieval-augmented motion diffusion model](https://doi.org/10.1109/ICCV51070.2023.00040) 93 | 94 | [Memorizing transformers](https://openreview.net/forum?id=TrjbxzRcnf-) 95 | 96 | [Audio captioning using pre-trained large-scale language model guided by audio-based similar caption retrieval](https://arxiv.org/abs/2012.07331) 97 | 98 | [Retrieval augmented convolutional encoder-decoder networks for video captioning](https://doi.org/10.1145/3539225) 99 | 100 | [Retrieval-augmented egocentric video captioning](https://doi.org/10.48550/arXiv.2401.00789) 101 | 102 | [Re-imagen: Retrievalaugmented text-to-image generator](https://arxiv.org/abs/2209.14491) 103 | 104 | [Knn-diffusion: Image generation via large-scale retrieval](https://arxiv.org/abs/2204.02849) 105 | 106 | [Retrieval-augmented diffusion models](https://proceedings.neurips.cc/paper_files/paper/2022/file/62868cc2fc1eb5cdf321d05b4b88510c-Paper-Conference.pdf) 107 | 108 | [Text-guided synthesis of artistic images with retrieval-augmented diffusion models](https://arxiv.org/abs/2207.13038) 109 | 110 | 111 | [Memory-driven text-to-image generation](https://arxiv.org/abs/2208.07022) 112 | 113 | [Mention memory: incorporating textual knowledge into transformers through entity mention attention](https://arxiv.org/abs/2110.06176) 114 | 115 | [Unlimiformer:Long-range transformers with unlimited length input](https://doi.org/10.48550/arXiv.2305.01625) 116 | 117 | [Entities as experts: Sparse memory access with entity supervision](https://arxiv.org/abs/2004.07202) 118 | 119 | [Amd: Anatomical motion diffusion with interpretable motion decomposition and fusion](https://arxiv.org/abs/2312.12763) 120 | 121 | [Retrieval-augmented text-to-audio generation](https://doi.org/10.48550/arXiv.2309.08051) 122 | 123 | [Concept-aware video captioning: Describing videos with effective prior information](https://doi.org/10.1109/TIP.2023.3307969) 124 | 125 | 126 | 127 | - Logit-based RAG 128 | 129 | 130 | 131 | [Generalization through memorization: Nearest neighbor language models](https://openreview.net/forum?id=HklBjCEKvH) 132 | 133 | 134 | 135 | [Syntax-Aware Retrieval Augmented Code Generation](https://aclanthology.org/2023.findings-emnlp.90) 136 | 137 | [Memory-augmented image captioning](https://aaai.org/papers/01317-memory-augmented-image-captioning/) 138 | 139 | [Retrieval-based neural source code summarization](https://doi.org/10.1145/3377811.3380383) 140 | 141 | [Efficient nearest neighbor language models](https://doi.org/10.18653/v1/2021.emnlp-main.461) 142 | 143 | 144 | 145 | [Nonparametric masked language modeling](https://doi.org/10.18653/v1/2023.findings-acl.132) 146 | 147 | 148 | 149 | [Editsum:A retrieve-and-edit framework for source code summarization](https://doi.org/10.1109/ASE51524.2021.9678724) 150 | 151 | 152 | 153 | - Speculative RAG 154 | 155 | [REST: Retrieval-Based Speculative Decoding](https://doi.org/10.48550/arXiv.2311.08252) 156 | 157 | [GPTCache](https://github.com/zilliztech/GPTCache) 158 | 159 | [COPY IS ALL YOU NEED](https://arxiv.org/abs/2307.06962) 160 | 161 | [RETRIEVAL IS ACCURATE GENERATION](https://arxiv.org/abs/2402.17532) 162 | 163 | ### RAG Enhancements 164 |
image 165 | 166 | - Input Enhancement 167 | 168 | - Query Transformations 169 | 170 | [Query2doc: Query Expansion with Large Language Models](https://aclanthology.org/2023.emnlp-main.585) 171 | 172 | [Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models](https://openreview.net/forum?id=vDvFT7IX4O) 173 | 174 | [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://doi.org/10.18653/v1/2023.acl-long.99) 175 | 176 | [RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation](https://arxiv.org/pdf/2404.00610) 177 | 178 | [Dynamic Contexts for Generating Suggestion Questions in RAG Based Conversational Systems](https://arxiv.org/pdf/2403.11413) 179 | 180 | - Data Augmentation 181 | 182 | [LESS: selecting influential data for targeted instruction tuning](https://arxiv.org/abs/2402.04333) 183 | 184 | [Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models](https://proceedings.mlr.press/v202/huang23i.html) 185 | 186 | [Telco-RAG: Navigating the challenges of retrieval-augmented language models for telecommunications](https://arxiv.org/pdf/2404.15939) 187 | 188 | 189 | 190 | - Retriever Enhancement 191 | 192 | - Recursive Retrieve 193 | 194 | [Query Expansion by Prompting Large Language Models](https://doi.org/10.48550/arXiv.2305.03653) 195 | 196 | [Rat: Retrieval augmented thoughts elicit context-aware reasoning in long-horizon generation](https://arxiv.org/abs/2403.05313) 197 | 198 | [React: Synergizing reasoning and acting in language models](https://arxiv.org/abs/2210.03629) 199 | 200 | [Chain-of-thought prompting elicits reasoning in large language models](https://arxiv.org/abs/2201.11903) 201 | 202 | 203 | 204 | 205 | 206 | [Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search](https://aclanthology.org/2023.findings-emnlp.86) 207 | 208 | [ACTIVERAG: Revealing the Treasures of Knowledge via Active Learning](https://arxiv.org/abs/2402.13547) 209 | 210 | [Retrieval-Augmented Thought Process as Sequential Decision Making](https://arxiv.org/abs/2402.07812) 211 | 212 | [In search of needles in a 10m haystack: Recurrent memory finds what llms miss](https://arxiv.org/abs/2402.10790v1) 213 | 214 | [Lost in the middle: How language models use long contexts](https://arxiv.org/abs/2307.03172) 215 | 216 | 217 | 218 | - Chunk Optimization 219 | 220 | [LlamaIndex](https://github.com/jerryjliu/llama_index) 221 | 222 | [RAPTOR: RECURSIVE ABSTRACTIVE PROCESSING FOR TREE-ORGANIZED RETRIEVAL](https://arxiv.org/pdf/2401.18059.pdf) 223 | 224 | [Prompt-RAG: Pioneering Vector Embedding-Free Retrieval-Augmented Generation in Niche Domains, Exemplified by Korean Medicine](https://arxiv.org/pdf/2401.11246) 225 | 226 | [Question-Based Retrieval using Atomic Units for Enterprise RAG](https://arxiv.org/pdf/2405.12363) 227 | 228 | - Finetune Retriever 229 | 230 | [C-Pack: Packaged Resources To Advance General Chinese Embedding](https://arxiv.org/abs/2309.07597) 231 | 232 | [BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://arxiv.org/abs/2402.03216) 233 | 234 | [LM-Cocktail: Resilient Tuning of Language Models via Model Merging](https://arxiv.org/abs/2311.13534) 235 | 236 | [Retrieve Anything To Augment Large Language Models](https://arxiv.org/abs/2310.07554) 237 | 238 | [Replug: Retrieval-augmented black-box language models](https://arxiv.org/abs/2301.12652) 239 | 240 | [When Language Model Meets Private Library](https://doi.org/10.18653/v1/2022.findings-emnlp.21) 241 | 242 | [EditSum: A Retrieve-and-Edit Framework for Source Code Summarization](https://doi.org/10.1109/ASE51524.2021.9678724) 243 | 244 | [Synchromesh: Reliable Code Generation from Pre-trained Language Models](https://openreview.net/forum?id=KmtVD97J43e) 245 | 246 | [Retrieval Augmented Convolutional Encoder-decoder Networks for Video Captioning](https://doi.org/10.1145/3539225) 247 | 248 | [Reinforcement learning for optimizing RAG for domain chatbots](https://arxiv.org/abs/2401.06800) 249 | 250 | - Hybrid Retrieve 251 | 252 | [RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair](https://doi.org/10.1145/3611643.3616256) 253 | 254 | [ReACC: A Retrieval-Augmented Code Completion Framework](https://doi.org/10.18653/v1/2022.acl-long.431) 255 | 256 | [Retrieval-based neural source code summarization](https://doi.org/10.1145/3377811.3380383) 257 | 258 | [BashExplainer: Retrieval-Augmented Bash Code Comment Generation based on Fine-tuned CodeBERT](https://doi.org/10.1109/ICSME55016.2022.00016) 259 | 260 | [Retrieval-Augmented Score Distillation for Text-to-3D Generation](https://doi.org/10.48550/arXiv.2402.02972) 261 | 262 | [Corrective Retrieval Augmented Generation](https://arxiv.org/abs/2401.15884) 263 | 264 | [Retrieval augmented generation with rich answer encoding](https://aclanthology.org/2023.ijcnlp-main.65.pdf) 265 | 266 | [Unims-rag: A unified multi-source retrieval-augmented generation for personalized dialogue systems](https://arxiv.org/abs/2401.13256) 267 | 268 | [You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval](https://arxiv.org/pdf/2403.07222v1) 269 | 270 | [Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers](https://arxiv.org/pdf/2404.07220) 271 | 272 | - Re-ranking 273 | 274 | [Re2G: Retrieve, Rerank, Generate](https://doi.org/10.18653/v1/2022.naacl-main.194) 275 | 276 | [Passage Re-ranking with BERT](http://arxiv.org/abs/1901.04085) 277 | 278 | [AceCoder: Utilizing Existing Code to Enhance Code Generation](https://arxiv.org/abs/2303.17780) 279 | 280 | [XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing](https://doi.org/10.18653/v1/2022.findings-emnlp.384) 281 | 282 | [A Fine-tuning Enhanced RAG System with Quantized Influence Measure as AI Judge](https://arxiv.org/abs/2402.17081v1) 283 | 284 | [UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers](https://arxiv.org/pdf/2303.00807.pdf) 285 | 286 | [Learning to Retrieve In-Context Examples for Large Language Models](https://arxiv.org/pdf/2307.07164.pdf) 287 | 288 | [The Chronicles of RAG: The Retriever, the Chunk and the Generator](https://arxiv.org/pdf/2401.07883.pdf) 289 | 290 | [Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases](https://arxiv.org/pdf/2403.10446) 291 | 292 | 293 | 294 | - Retrieval Transformation 295 | 296 | [Learning to filter context for retrieval-augmented generation](https://arxiv.org/abs/2311.08377) 297 | 298 | [Fid-light: Efficient and effective retrieval-augmented text generation](https://arxiv.org/abs/2209.14290) 299 | 300 | [Gar-meets-rag paradigm for zero-shot information retrieval](https://arxiv.org/abs/2310.20158) 301 | 302 | - Others 303 | 304 | [PineCone](https://www.pinecone.io) 305 | 306 | [Generate rather than retrieve: Large language models are strong context generators](https://arxiv.org/abs/2209.10063) 307 | 308 | [Generator-retriever-generator: A novel approach to open-domain question answering](https://arxiv.org/abs/2307.11278) 309 | 310 | [Multi-Head RAG: Solving Multi-Aspect Problems with LLMs](https://arxiv.org/pdf/2406.05085) 311 | 312 | - Generator Enhancement 313 | 314 | - Prompt Engineering 315 | 316 | [Prompt Engineering Guide](https://github.com/dair-ai/Prompt-Engineering-Guide) 317 | 318 | [Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models](https://doi.org/10.48550/arXiv.2310.06117) 319 | 320 | [Active Prompting with Chain-of-Thought for Large Language Models](https://doi.org/10.48550/arXiv.2302.12246) 321 | 322 | [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](http://papers.nips.cc/paper\_files/paper/2022/hash/9d5609613524ecf4f15af0f7b31abca4-Abstract-Conference.html) 323 | 324 | [LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models](https://aclanthology.org/2023.emnlp-main.825) 325 | 326 | [Lost in the Middle: How Language Models Use Long Contexts](https://doi.org/10.48550/arXiv.2307.03172) 327 | 328 | [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://doi.org/10.1109/ICCV51070.2023.00040) 329 | 330 | [Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)](https://arxiv.org/abs/2304.06815) 331 | 332 | [Retrieval-Based Prompt Selection for Code-Related Few-Shot Learning](https://doi.org/10.1109/ICSE48619.2023.00205) 333 | 334 | [XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing](https://doi.org/10.18653/v1/2022.findings-emnlp.384) 335 | 336 | [Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models](https://proceedings.mlr.press/v202/huang23i.html) 337 | 338 | - Decoding Tuning 339 | 340 | [InferFix: End-to-End Program Repair with LLMs](https://doi.org/10.1145/3611643.3613892) 341 | 342 | [Synchromesh: Reliable Code Generation from Pre-trained Language Models](https://openreview.net/forum?id=KmtVD97J43e) 343 | 344 | 345 | - Finetune Generator 346 | 347 | [Improving Language Models by Retrieving from Trillions of Tokens](https://proceedings.mlr.press/v162/borgeaud22a.html) 348 | 349 | [When Language Model Meets Private Library](https://doi.org/10.18653/v1/2022.findings-emnlp.21) 350 | 351 | [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://arxiv.org/abs/2203.13474) 352 | 353 | [Concept-Aware Video Captioning: Describing Videos With Effective Prior Information](https://doi.org/10.1109/TIP.2023.3307969) 354 | 355 | [Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation](https://doi.org/10.48550/arXiv.2307.06940) 356 | 357 | [Lora: Low-rank adaptation of large language models](https://arxiv.org/abs/2106.09685) 358 | 359 | [Retrieval-Augmented Score Distillation for Text-to-3D Generation](https://doi.org/10.48550/arXiv.2402.02972) 360 | 361 | - Result Enhancement 362 | 363 | - Rewrite Output 364 | 365 | [Automated Code Editing with Search-Generate-Modify](https://doi.org/10.48550/arXiv.2306.06490) 366 | 367 | [Repair Is Nearly Generation: Multilingual Program Repair with LLMs](https://doi.org/10.1609/aaai.v37i4.25642) 368 | 369 | [Case-based Reasoning for Natural Language Queries over Knowledge Bases](https://doi.org/10.18653/v1/2021.emnlp-main.755) 370 | 371 | - RAG Pipeline Enhancement 372 | 373 | - Adaptive Retrieval 374 | 375 | - Rule-Baesd 376 | 377 | [Active retrieval augmented generation](https://arxiv.org/abs/2305.06983) 378 | 379 | [Efficient Nearest Neighbor Language Models](https://doi.org/10.18653/v1/2021.emnlp-main.461) 380 | 381 | [Generalization through Memorization: Nearest Neighbor Language Models](https://arxiv.org/abs/1911.00172) 382 | 383 | [Nonparametric masked language modeling](https://arxiv.org/abs/2212.01349) 384 | 385 | [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://doi.org/10.18653/v1/2023.acl-long.546) 386 | 387 | [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://doi.org/10.1162/tacl\_a\_00407) 388 | 389 | [Large Language Models Struggle to Learn Long-Tail Knowledge](https://proceedings.mlr.press/v202/kandpal23a.html) 390 | 391 | - Model-Based 392 | 393 | [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://doi.org/10.48550/arXiv.2310.11511) 394 | 395 | [Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation](https://doi.org/10.48550/arXiv.2307.11019) 396 | 397 | [Self-Knowledge Guided Retrieval Augmentation for Large Language Models](https://aclanthology.org/2023.findings-emnlp.691) 398 | 399 | [Retrieve only when it needs: Adaptive retrieval augmentation for hallucination mitigation in large language models](https://arxiv.org/abs/2402.10612) 400 | 401 | [Adaptive-rag: Learning to adapt retrieval-augmented large language models through question complexity](https://arxiv.org/abs/2403.14403) 402 | 403 | - Iterative RAG 404 | 405 | [RepoCoder: Repository-Level Through Iterative Retrieval and Generation](https://aclanthology.org/2023.emnlp-main.151) 406 | 407 | [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://aclanthology.org/2023.findings-emnlp.620) 408 | 409 | [Knowledge graph based synthetic corpus generation for knowledge-enhanced language model pre-training](https://arxiv.org/abs/2010.12688) 410 | 411 | 412 | ## Applications Taxonomy 413 |
image 414 |
image 415 | 416 | ### RAG for Text 417 | - Question Answering 418 | 419 | [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://doi.org/10.18653/v1/2021.eacl-main.74) 420 | 421 | [REALM: Retrieval-Augmented Language Model Pre-Training](https://arxiv.org/abs/2002.08909) 422 | 423 | [Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training](https://doi.org/10.18653/v1/2021.naacl-main.278) 424 | 425 | [Atlas: Few-shot Learning with Retrieval Augmented Language Models](http://jmlr.org/papers/v24/23-0037.html) 426 | 427 | [Improving Language Models by Retrieving from Trillions of Tokens](https://proceedings.mlr.press/v162/borgeaud22a.html) 428 | 429 | [Self-Knowledge Guided Retrieval Augmentation for Large Language Models](https://aclanthology.org/2023.findings-emnlp.691) 430 | 431 | [Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering](https://doi.org/10.48550/arXiv.2306.04136) 432 | 433 | [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model with Knowledge Graph](https://doi.org/10.48550/arXiv.2307.07697) 434 | 435 | [Nonparametric Masked Language Modeling](https://doi.org/10.18653/v1/2023.findings-acl.132) 436 | 437 | [CL-ReLKT: Cross-lingual Language Knowledge Transfer for Multilingual Retrieval Question Answering](https://doi.org/10.18653/v1/2022.findings-naacl.165) 438 | 439 | [One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval](https://proceedings.neurips.cc/paper/2021/hash/3df07fdae1ab273a967aaa1d355b8bb6-Abstract.html) 440 | 441 | [Entities as Experts: Sparse Memory Access with Entity Supervision](https://arxiv.org/abs/2004.07202) 442 | 443 | [When to Read Documents or QA History: On Unified and Selective Open-domain QA](https://doi.org/10.18653/v1/2023.findings-acl.401) 444 | 445 | [Enhancing LLM Intelligence with ARM-RAG: Auxiliary Rationale Memory for Retrieval Augmented Generation](https://arxiv.org/abs/2311.04177) 446 | 447 | [DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Service](https://arxiv.org/pdf/2309.11325.pdf) 448 | 449 | - Fact verification 450 | 451 | [CONCRETE: Improving Cross-lingual Fact-checking with Cross-lingual Retrieval](https://aclanthology.org/2022.coling-1.86) 452 | 453 | [Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization](https://arxiv.org/pdf/2405.02816) 454 | 455 | - Commonsense Reasoning 456 | 457 | [KG-BART: Knowledge Graph-Augmented {BART} for Generative Commonsense Reasoning](https://doi.org/10.1609/aaai.v35i7.16796) 458 | 459 | [What Evidence Do Language Models Find Convincing?](https://arxiv.org/abs/2402.11782v1) 460 | 461 | [Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models](https://arxiv.org/abs/2310.04027) 462 | 463 | - Human-Machine Conversation 464 | 465 | [Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs](https://doi.org/10.18653/v1/2020.acl-main.184) 466 | 467 | [Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory](https://doi.org/10.18653/v1/n19-1124) 468 | 469 | [Internet-Augmented Dialogue Generation](https://doi.org/10.18653/v1/2022.acl-long.579) 470 | 471 | [BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage](https://doi.org/10.48550/arXiv.2208.03188) 472 | 473 | [A Model of Cross-Lingual Knowledge-Grounded Response Generation for Open-Domain Dialogue Systems](https://doi.org/10.18653/v1/2021.findings-emnlp.33) 474 | 475 | [From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICL](https://openreview.net/forum?id=KLPLCXo4aD) 476 | 477 | [Cross-Lingual Retrieval Augmented Prompt for Low-Resource Languages](https://aclanthology.org/2023.findings-acl.528/) 478 | 479 | [Citation-Enhanced Generation for LLM-based Chatbot](https://arxiv.org/pdf/2402.16063v1.pdf) 480 | 481 | [KAUCUS: Knowledge Augmented User Simulators for Training Language Model Assistants](https://aclanthology.org/2024.scichat-1.5/) 482 | 483 | 484 | 485 | - Neural Machine Translation 486 | 487 | [Neural Machine Translation with Monolingual Translation Memory](https://doi.org/10.18653/v1/2021.acl-long.567) 488 | 489 | [Nearest Neighbor Machine Translation](https://openreview.net/forum?id=7wCBOfJ8hJM) 490 | 491 | [Training Language Models with Memory Augmentation](https://doi.org/10.18653/v1/2022.emnlp-main.382) 492 | 493 | - Event Extraction 494 | 495 | [Retrieval-Augmented Generative Question Answering for Event Argument Extraction](https://doi.org/10.18653/v1/2022.emnlp-main.307) 496 | 497 | - Summarization 498 | 499 | [Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training](https://doi.org/10.18653/v1/2022.findings-naacl.92) 500 | 501 | [Unlimiformer: Long-Range Transformers with Unlimited Length Input](https://doi.org/10.48550/arXiv.2305.01625) 502 | 503 | [Retrieval-based Full-length Wikipedia Generation for Emergent Events](https://arxiv.org/abs/2402.18264v1) 504 | 505 | [RIGHT: Retrieval-augmented Generation for Mainstream Hashtag Recommendation](https://arxiv.org/abs/2312.10466) 506 | 507 | [M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions](https://arxiv.org/pdf/2405.16420) 508 | 509 | ### RAG for Code 510 | - Code Generation 511 | 512 | [Retrieval-Based Neural Code Generation](https://doi.org/10.18653/v1/d18-1111) 513 | 514 | [Retrieval Augmented Code Generation and Summarization](https://doi.org/10.18653/v1/2021.findings-emnlp.232) 515 | 516 | [When Language Model Meets Private Library](https://doi.org/10.18653/v1/2022.findings-emnlp.21) 517 | 518 | [Language Models of Code are Few-Shot Commonsense Learners](https://doi.org/10.18653/v1/2022.emnlp-main.90) 519 | 520 | [DocPrompting: Generating Code by Retrieving the Docs](https://openreview.net/pdf?id=ZTCxT2t2Ru) 521 | 522 | [CodeT5+: Open Code Large Language Models for Code Understanding and Generation](https://aclanthology.org/2023.emnlp-main.68) 523 | 524 | [AceCoder: Utilizing Existing Code to Enhance Code Generation](https://arxiv.org/abs/2303.17780) 525 | 526 | [Syntax-Aware Retrieval Augmented Code Generation](https://aclanthology.org/2023.findings-emnlp.90) 527 | 528 | [A^3-CodGen: A Repository-Level Code Generation Framework for Code Reuse with Local-Aware, Global-Aware, and Third-Party-Library-Aware](https://arxiv.org/abs/2312.05772) 529 | 530 | [SkCoder: A Sketch-based Approach for Automatic Code Generation](https://ieeexplore.ieee.org/abstract/document/10172719) 531 | 532 | [CodeGen4Libs: A Two-Stage Approach for Library-Oriented Code Generation](https://ieeexplore.ieee.org/abstract/document/10298327) 533 | 534 | [ToolCoder: Teach Code Generation Models to use API search tools](https://arxiv.org/abs/2305.04032) 535 | 536 | [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://arxiv.org/abs/2401.07339) 537 | 538 | [RRGcode: Deep hierarchical search-based code generation](https://www.sciencedirect.com/science/article/pii/S0164121224000256) 539 | 540 | [Code Search Is All You Need? Improving Code Suggestions with Code Search](https://www.computer.org/csdl/proceedings-article/icse/2024/021700a857/1V5BkjI3196) 541 | 542 | [ARKS: Active Retrieval in Knowledge Soup for Code Generation](https://arxiv.org/abs/2402.12317) 543 | 544 | - Code Summary 545 | 546 | [Retrieval-based neural source code summarization](https://doi.org/10.1145/3377811.3380383) 547 | 548 | [Retrieve and Refine: Exemplar-based Neural Comment Generation](https://doi.org/10.1145/3324884.3416578) 549 | 550 | [EditSum: A Retrieve-and-Edit Framework for Source Code Summarization](https://doi.org/10.1109/ASE51524.2021.9678724) 551 | 552 | [Retrieval-Augmented Generation for Code Summarization via Hybrid GNN](https://openreview.net/forum?id=zv-typ1gPxA) 553 | 554 | [Context-aware Retrieval-based Deep Commit Message Generation](https://dl.acm.org/doi/abs/10.1145/3464689) 555 | 556 | [RACE: Retrieval-augmented Commit Message Generation](https://doi.org/10.18653/v1/2022.emnlp-main.372) 557 | 558 | [BashExplainer: Retrieval-Augmented Bash Code Comment Generation based on Fine-tuned CodeBERT](https://doi.org/10.1109/ICSME55016.2022.00016) 559 | 560 | [Retrieval-Based Transformer Pseudocode Generation](https://www.mdpi.com/2227-7390/10/4/604) 561 | 562 | [A Simple Retrieval-based Method for Code Comment Generation](https://ieeexplore.ieee.org/abstract/document/9825803) 563 | 564 | [READSUM: Retrieval-Augmented Adaptive Transformer for Source Code Summarization](https://ieeexplore.ieee.org/abstract/document/10113620) 565 | 566 | [Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization](https://arxiv.org/abs/2305.11074) 567 | 568 | [Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)](https://arxiv.org/abs/2304.06815) 569 | 570 | [Cross-Modal Retrieval-Enhanced Code Summarization based on Joint Learning for Retrieval and Generation](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4724884) 571 | 572 | [Automatic Smart Contract Comment Generation via Large Language Models and In-Context Learning](https://www.sciencedirect.com/science/article/pii/S0950584924000107) 573 | 574 | [UniLog: Automatic Logging via LLM and In-Context Learning](https://dl.acm.org/doi/abs/10.1145/3597503.3623326) 575 | 576 | - Code Completion 577 | 578 | [A Retrieve-and-Edit Framework for Predicting Structured Outputs](https://proceedings.neurips.cc/paper_files/paper/2018/hash/cd17d3ce3b64f227987cd92cd701cc58-Abstract.html) 579 | 580 | [Generating Code with the Help of Retrieved Template Functions and Stack Overflow Answers](https://arxiv.org/abs/2104.05310) 581 | 582 | [ReACC: A Retrieval-Augmented Code Completion Framework](https://doi.org/10.18653/v1/2022.acl-long.431) 583 | 584 | [Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases](https://ieeexplore.ieee.org/abstract/document/10298575) 585 | 586 | [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://aclanthology.org/2023.emnlp-main.151) 587 | 588 | [CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context](https://doi.org/10.48550/arXiv.2212.10007) 589 | 590 | [RepoFusion: Training Code Models to Understand Your Repository](https://arxiv.org/abs/2306.10998) 591 | 592 | [Revisiting and Improving Retrieval-Augmented Deep Assertion Generation](https://ieeexplore.ieee.org/abstract/document/10298588) 593 | 594 | [De-Hallucinator: Iterative Grounding for LLM-Based Code Completion](https://arxiv.org/abs/2401.01701) 595 | 596 | [REPOFUSE: Repository-Level Code Completion with Fused Dual Context](https://arxiv.org/abs/2402.14323) 597 | 598 | - Automatic Program Repair 599 | 600 | [Repair Is Nearly Generation: Multilingual Program Repair with LLMs](https://doi.org/10.1609/aaai.v37i4.25642) 601 | 602 | [Retrieval-Based Prompt Selection for Code-Related Few-Shot Learning](https://doi.org/10.1109/ICSE48619.2023.00205) 603 | 604 | [InferFix: End-to-End Program Repair with LLMs](https://doi.org/10.1145/3611643.3613892) 605 | 606 | [RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair](https://dl.acm.org/doi/abs/10.1145/3611643.3616256) 607 | 608 | [Automated Code Editing with Search-Generate-Modify](https://arxiv.org/abs/2306.06490) 609 | 610 | [RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Models](https://arxiv.org/abs/2311.16543) 611 | 612 | - Text-to-SQL and Code-based Semantic Parsing 613 | 614 | [XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing](https://doi.org/10.18653/v1/2022.findings-emnlp.384) 615 | 616 | [Synchromesh: Reliable Code Generation from Pre-trained Language Models](https://openreview.net/forum?id=KmtVD97J43e) 617 | 618 | [Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing](https://aclanthology.org/2022.emnlp-main.624/) 619 | 620 | [RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL](https://ojs.aaai.org/index.php/AAAI/article/view/26535) 621 | 622 | [Leveraging Code to Improve In-context Learning for Semantic Parsing](https://arxiv.org/abs/2311.09519) 623 | 624 | [ReFSQL: A Retrieval-Augmentation Framework for Text-to-SQL Generation](https://aclanthology.org/2023.findings-emnlp.48/) 625 | 626 | [Enhancing Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies](https://aclanthology.org/2023.findings-emnlp.996/) 627 | 628 | [Selective Demonstrations for Cross-domain Text-to-SQL](https://aclanthology.org/2023.findings-emnlp.944/) 629 | 630 | [DBCopilot: Scaling Natural Language Querying to Massive Databases via Schema Routing](https://arxiv.org/abs/2312.03463) 631 | 632 | [Multi-Hop Table Retrieval for Open-Domain Text-to-SQL](https://arxiv.org/abs/2402.10666) 633 | 634 | [CodeS: Towards Building Open-source Language Models for Text-to-SQL](https://arxiv.org/abs/2402.16347) 635 | 636 | - Others 637 | 638 | [De-fine: Decomposing and Refining Visual Programs with Auto-Feedback](https://arxiv.org/abs/2311.12890) 639 | 640 | [Leveraging training data in few-shot prompting for numerical reasoning](https://arxiv.org/abs/2305.18170) 641 | 642 | [Retrieval-Augmented Code Generation for Universal Information Extraction](https://arxiv.org/abs/2311.02962) 643 | 644 | [E&V: Prompting Large Language Models to Perform Static Analysis by Pseudo-code Execution and Verification](https://arxiv.org/abs/2312.08477) 645 | 646 | [Lessons from Building StackSpot AI: A Contextualized AI Coding Assistant](https://arxiv.org/abs/2311.18450) 647 | 648 | [Testing the Limits: Unusual Text Inputs Generation for Mobile App Crash Detection with Large Language Model](https://arxiv.org/abs/2310.15657) 649 | 650 | ### RAG for Audio 651 | - Audio Generation 652 | 653 | [Retrieval-Augmented Text-to-Audio Generation](https://doi.org/10.48550/arXiv.2309.08051) 654 | 655 | [Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://doi.org/10.1109/ICASSP49357.2023.10095969) 656 | 657 | [Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models](https://proceedings.mlr.press/v202/huang23i.html) 658 | 659 | - Audio Captioning 660 | 661 | [RECAP: Retrieval-Augmented Audio Captioning](https://doi.org/10.48550/arXiv.2309.09836) 662 | 663 | [Audio Captioning using Pre-Trained Large-Scale Language Model Guided by Audio-based Similar Caption Retrieval](https://arxiv.org/abs/2012.07331) 664 | 665 | [Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://doi.org/10.1109/ICASSP49357.2023.10095969) 666 | 667 | [CNN architectures for large-scale audio classification](https://doi.org/10.1109/ICASSP.2017.7952132) 668 | 669 | [Natural language supervision for general-purpose audio representations](https://ieeexplore.ieee.org/abstract/document/10448504) 670 | 671 | [Weakly-supervised Automated Audio Captioning via text only training](https://arxiv.org/abs/2309.12242) 672 | 673 | [Training Audio Captioning Models without Audio](https://ieeexplore.ieee.org/abstract/document/10448115) 674 | 675 | ### RAG for Image 676 | - Image Generation 677 | 678 | [Retrievegan: Image synthesis via differentiable patch retrieval](https://arxiv.org/abs/2007.08513) 679 | 680 | [Instance-conditioned gan](https://arxiv.org/abs/2109.05070) 681 | 682 | [Memory-driven text-to-image generation](https://arxiv.org/abs/2208.07022) 683 | 684 | [Re-imagen: Retrieval-augmented text-to-image generator](https://arxiv.org/abs/2209.14491) 685 | 686 | [KNN-Diffusion: Image Generation via Large-Scale Retrieval](https://arxiv.org/abs/2204.02849) 687 | 688 | [Retrieval-Augmented Diffusion Models](https://arxiv.org/abs/2204.11824) 689 | 690 | [Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models](https://arxiv.org/abs/2207.13038) 691 | 692 | [X&Fuse: Fusing Visual Information in Text-to-Image Generation](https://arxiv.org/abs/2303.01000) 693 | 694 | [Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs](https://arxiv.org/abs/2401.11708) 695 | 696 | - Image Captioning 697 | 698 | [Memory-augmented image captioning](https://ojs.aaai.org/index.php/AAAI/article/view/16220) 699 | 700 | [Retrieval-enhanced adversarial training with dynamic memory-augmented attention for image paragraph captioning](https://www.sciencedirect.com/science/article/pii/S0950705120308595) 701 | 702 | [Retrieval-Augmented Transformer for Image Captioning](https://arxiv.org/abs/2207.13162) 703 | 704 | [Retrieval-augmented image captioning](https://arxiv.org/abs/2302.08268) 705 | 706 | [Reveal: Retrieval-augmented visual-language pre-training with multi-source multimodal knowledge memory](https://arxiv.org/abs/2212.05221) 707 | 708 | [SmallCap: Lightweight Image Captioning Prompted With Retrieval Augmentation](https://arxiv.org/abs/2209.15323) 709 | 710 | [Cross-Modal Retrieval and Semantic Refinement for Remote Sensing Image Captioning](https://www.mdpi.com/2072-4292/16/1/196) 711 | 712 | - Others 713 | 714 | [An empirical study of gpt-3 for few-shot knowledge-based vqa](https://ojs.aaai.org/index.php/AAAI/article/view/20215) 715 | 716 | [Retrieval augmented visual question answering with outside knowledge](https://aclanthology.org/2022.emnlp-main.772/) 717 | 718 | [Augmenting transformers with KNN-based composite memory for dialog](https://doi.org/10.1162/tacl_a_00356) 719 | 720 | [Maria: A visual experience powered conversational agent](https://aclanthology.org/2021.acl-long.435/) 721 | 722 | [Neural machine translation with phrase-level universal visual representations](https://aclanthology.org/2022.acl-long.390/) 723 | 724 | 725 | ### RAG for Video 726 | - Video Captioning 727 | 728 | [Incorporating Background Knowledge into Video Description Generation](https://aclanthology.org/D18-1433/) 729 | 730 | [Retrieval Augmented Convolutional Encoder-decoder Networks for Video Captioning](https://doi.org/10.1145/3539225) 731 | 732 | [Concept-Aware Video Captioning: Describing Videos With Effective Prior Information](https://doi.org/10.1109/TIP.2023.3307969) 733 | 734 | [Retrieval-Augmented Egocentric Video Captioning](https://arxiv.org/abs/2401.00789) 735 | 736 | - Video QA&Dialogue 737 | 738 | [Memory augmented deep recurrent neural network for video question answering](https://doi.org/10.1109/TNNLS.2019.2938015) 739 | 740 | [Retrieving-to-answer: Zero-shot video question answering with frozen large language models](https://openaccess.thecvf.com/content/ICCV2023W/MMFM/html/Pan_Retrieving-to-Answer_Zero-Shot_Video_Question_Answering_with_Frozen_Large_Language_Models_ICCVW_2023_paper.html) 741 | 742 | [Tvqa+: Spatio-temporal grounding for video question answering](https://aclanthology.org/2020.acl-main.730/) 743 | 744 | [Vgnmn: Video-grounded neural module networks for video-grounded dialogue systems](https://aclanthology.org/2022.naacl-main.247/) 745 | 746 | - Others 747 | 748 | [Language models with image descriptors are strong few-shot video-language learners](https://proceedings.neurips.cc/paper_files/paper/2022/hash/381ceeae4a1feb1abc59c773f7e61839-Abstract-Conference.html) 749 | 750 | [RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model](https://arxiv.org/abs/2402.10828) 751 | 752 | [Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation](https://doi.org/10.48550/arXiv.2307.06940) 753 | 754 | [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://doi.org/10.1109/ICCV48922.2021.00175) 755 | 756 | ### RAG for 3D 757 | - Text-to-3D 758 | 759 | [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://doi.org/10.1109/ICCV51070.2023.00040) 760 | 761 | [AMD: Anatomical Motion Diffusion with Interpretable Motion Decomposition and Fusion](https://arxiv.org/abs/2312.12763) 762 | 763 | [Retrieval-Augmented Score Distillation for Text-to-3D Generation](https://doi.org/10.48550/arXiv.2402.02972) 764 | 765 | ### RAG for Knowledge 766 | - Knowledge Base Question Answering 767 | 768 | [ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering](https://doi.org/10.18653/v1/2021.acl-demo.39) 769 | 770 | [Unseen Entity Handling in Complex Question Answering over Knowledge Base via Language Generation](https://aclanthology.org/2021.findings-emnlp.50/) 771 | 772 | [Case-based Reasoning for Natural Language Queries over Knowledge Bases](https://doi.org/10.18653/v1/2021.emnlp-main.755) 773 | 774 | [Logical Form Generation via Multi-task Learning for Complex Question Answering over Knowledge Bases](https://aclanthology.org/2022.coling-1.145) 775 | 776 | [Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database](https://aclanthology.org/2022.emnlp-main.605/) 777 | 778 | [RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering](https://aclanthology.org/2022.acl-long.417/) 779 | 780 | [TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Base](https://aclanthology.org/2022.emnlp-main.555/) 781 | 782 | [DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases](https://openreview.net/forum?id=XHc5zRPxqV9) 783 | 784 | [End-to-end Case-Based Reasoning for Commonsense Knowledge Base Completion](https://aclanthology.org/2023.eacl-main.255/) 785 | 786 | [Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA](https://dl.acm.org/doi/abs/10.1145/3583780.3615150) 787 | 788 | [Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering](https://arxiv.org/abs/2308.13259) 789 | 790 | [Few-shot Transfer Learning for Knowledge Base Question Answering: Fusing Supervised Models with In-Context Learning](https://arxiv.org/abs/2311.08894) 791 | 792 | [FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering](https://aclanthology.org/2023.acl-long.57/) 793 | 794 | [Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering](https://aclanthology.org/2023.nlrse-1.7/) 795 | 796 | [Knowledge Graph-augmented Language Models for Complex Question Answering](https://aclanthology.org/2023.nlrse-1.1/) 797 | 798 | [Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering](https://arxiv.org/abs/2309.11206) 799 | 800 | [Distribution Shifts Are Bottlenecks: Extensive Evaluation for Grounding Language Models to Knowledge Bases](https://aclanthology.org/2024.eacl-srw.7/) 801 | 802 | [Probing Structured Semantics Understanding and Generation of Language Models via Question Answering](https://arxiv.org/abs/2401.05777) 803 | 804 | [Keqing: Knowledge-based Question Answering is A Nature Chain-of-Thought mentor of LLMs](https://arxiv.org/abs/2401.00426) 805 | 806 | [Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models](https://arxiv.org/abs/2402.15131) 807 | 808 | - Knowledge-augmented Open-domain Question Answering 809 | 810 | [UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering](https://aclanthology.org/2022.findings-naacl.115/) 811 | 812 | [KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering](https://aclanthology.org/2022.acl-long.340/) 813 | 814 | [Empowering Language Models with Knowledge Graph Reasoning for Open-Domain Question Answering](https://aclanthology.org/2022.emnlp-main.650/) 815 | 816 | [Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering](https://aclanthology.org/2022.findings-emnlp.13/) 817 | 818 | [Enhancing Multi-modal Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation](https://dl.acm.org/doi/abs/10.1145/3581783.3611964) 819 | 820 | [DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text](https://arxiv.org/abs/2310.20170) 821 | 822 | [KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases](https://arxiv.org/abs/2308.11761) 823 | 824 | [Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering](https://arxiv.org/abs/2403.02966) 825 | 826 | [Two-stage Generative Question Answering on Temporal Knowledge Graph Using Large Language Models](https://arxiv.org/abs/2402.16568) 827 | 828 | [KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph](https://arxiv.org/abs/2312.15880) 829 | 830 | [GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning](https://arxiv.org/pdf/2405.20139) 831 | 832 | - Table Question Answering 833 | 834 | [NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned](https://proceedings.mlr.press/v133/min21a.html) 835 | 836 | [Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering](https://aclanthology.org/2021.acl-long.315/) 837 | 838 | [End-to-End Table Question Answering via Retrieval-Augmented Generation](https://arxiv.org/abs/2203.16714) 839 | 840 | [OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering](https://aclanthology.org/2022.naacl-main.68/) 841 | 842 | [Reasoning over Hybrid Chain for Table-and-Text Open Domain Question Answering](https://www.ijcai.org/proceedings/2022/0629.pdf) 843 | 844 | [Conversational Question Answering on Heterogeneous Sources](https://dl.acm.org/doi/abs/10.1145/3477495.3531815) 845 | 846 | [Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge](https://aclanthology.org/2022.findings-emnlp.392/) 847 | 848 | [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://aclanthology.org/2023.emnlp-main.574/) 849 | 850 | [cTBLS: Augmenting Large Language Models with Conversational Tables](https://aclanthology.org/2023.nlp4convai-1.6/) 851 | 852 | [RINK: Reader-Inherited Evidence Reranker for Table-and-Text Open Domain Question Answering](https://ojs.aaai.org/index.php/AAAI/article/view/26577) 853 | 854 | [Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables](https://aclanthology.org/2023.findings-ijcnlp.1/) 855 | 856 | [Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data](https://arxiv.org/abs/2402.12869) 857 | 858 | [ERATTA: Extreme RAG for Table To Answers with Large Language Models](https://arxiv.org/pdf/2405.03963) 859 | 860 | - Others 861 | 862 | [Improving Knowledge-Aware Dialogue Response Generation by Using Human-Written Prototype Dialogues](https://aclanthology.org/2020.findings-emnlp.126/) 863 | 864 | [Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation](https://arxiv.org/abs/2305.18846) 865 | 866 | [RHO: Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding](https://aclanthology.org/2023.findings-acl.275/) 867 | 868 | [Retrieval-Enhanced Generative Model for Large-Scale Knowledge Graph Completion](https://doi.org/10.1145/3539618.3592052) 869 | 870 | [Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestion](https://arxiv.org/abs/2311.06318) 871 | 872 | [G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering](https://arxiv.org/abs/2402.07630) 873 | 874 | [RAG-based Explainable Prediction of Road Users Behaviors for Automated Driving using Knowledge Graphs and Large Language Models](https://arxiv.org/pdf/2405.00449) 875 | 876 | [HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models](https://arxiv.org/pdf/2405.14831) 877 | 878 | ### RAG for Science 879 | - Drug Discovery 880 | 881 | [Retrieval-based controllable molecule generation](https://arxiv.org/abs/2208.11126) 882 | 883 | [Prompt-based 3d molecular diffusion models for structure-based drug design](https://openreview.net/forum?id=FWsGuAFn3n) 884 | 885 | - Biomedical Informatics Enhancement 886 | 887 | [PoET: A generative model of protein families as sequences-of-sequences](https://proceedings.neurips.cc/paper_files/paper/2023/hash/f4366126eba252699b280e8f93c0ab2f-Abstract-Conference.html) 888 | 889 | [Retrieval-augmented large language models for adolescent idiopathic scoliosis patients in shared decision-making](https://dl.acm.org/doi/abs/10.1145/3584371.3612956) 890 | 891 | [BioReader: a Retrieval-Enhanced Text-to-Text Transformer for Biomedical Literature](https://aclanthology.org/2022.emnlp-main.390/) 892 | 893 | [Writing by Memorizing: Hierarchical Retrieval-based Medical Report Generation](https://arxiv.org/abs/2106.06471) 894 | 895 | [From RAG to QA-RAG: Integrating Generative AI for Pharmaceutical Regulatory Compliance Process](https://arxiv.org/abs/2402.01717) 896 | 897 | [RAG-RLRC-LaySum at BioLaySumm: Integrating Retrieval-Augmented Generation and Readability Control for Layman Summarization of Biomedical Texts](https://arxiv.org/pdf/2405.13179) 898 | 899 | - Math Applications 900 | 901 | [Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference](https://arxiv.org/abs/2310.03184) 902 | 903 | [LeanDojo: Theorem Proving with Retrieval-Augmented Language Models](https://proceedings.neurips.cc/paper_files/paper/2023/hash/4441469427094f8873d0fecb0c4e1cee-Abstract-Datasets_and_Benchmarks.html) 904 | 905 | ## Benchmark 906 | [Benchmarking Large Language Models in Retrieval-Augmented Generation](https://doi.org/10.48550/arXiv.2309.01431) 907 | 908 | [CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models](https://doi.org/10.48550/arXiv.2401.17043) 909 | 910 | [ARES: An Automated Evaluation Framework for Retrieval-AugmentedGeneration Systems](https://doi.org/10.48550/arXiv.2311.09476) 911 | 912 | [RAGAS: Automated Evaluation of Retrieval Augmented Generation](https://doi.org/10.48550/arXiv.2309.15217) 913 | 914 | [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://arxiv.org/abs/2009.02252) 915 | 916 | 917 | ## Citation 918 | if you find this work useful, please cite our paper: 919 | ``` 920 | @article{zhao2024retrieval, 921 | title={Retrieval-Augmented Generation for AI-Generated Content: A Survey}, 922 | author={Zhao, Penghao and Zhang, Hailin and Yu, Qinhan and Wang, Zhengren and Geng, Yunteng and Fu, Fangcheng and Yang, Ling and Zhang, Wentao and Cui, Bin}, 923 | journal={arXiv preprint arXiv:2402.19473}, 924 | year={2024} 925 | } 926 | ``` 927 | 928 | 929 | --------------------------------------------------------------------------------