{"id":13641066,"url":"https://github.com/hymie122/RAG-Survey","last_synced_at":"2025-04-20T07:31:52.103Z","repository":{"id":225260744,"uuid":"762204955","full_name":"hymie122/RAG-Survey","owner":"hymie122","description":"Collecting awesome papers of RAG for AIGC.  We propose a taxonomy of RAG foundations, enhancements, and applications in paper \"Retrieval-Augmented Generation for AI-Generated Content: A Survey\".","archived":false,"fork":false,"pushed_at":"2024-08-20T11:52:42.000Z","size":6804,"stargazers_count":1016,"open_issues_count":1,"forks_count":78,"subscribers_count":23,"default_branch":"main","last_synced_at":"2024-08-20T13:53:56.908Z","etag":null,"topics":["aigc","diffusion-models","llm","multimodality","rag","survey"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hymie122.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-02-23T09:47:08.000Z","updated_at":"2024-08-20T11:52:46.000Z","dependencies_parsed_at":"2024-06-22T02:29:46.497Z","dependency_job_id":"b02a304d-88f3-40af-84c8-7aa4ab0c0567","html_url":"https://github.com/hymie122/RAG-Survey","commit_stats":null,"previous_names":["hymie122/rag-survey"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hymie122%2FRAG-Survey","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hymie122%2FRAG-Survey/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hymie122%2FRAG-Survey/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hymie122%2FRAG-Survey/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hymie122","download_url":"https://codeload.github.com/hymie122/RAG-Survey/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223822029,"owners_count":17208788,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["aigc","diffusion-models","llm","multimodality","rag","survey"],"created_at":"2024-08-02T01:01:17.430Z","updated_at":"2024-11-09T11:30:42.292Z","avatar_url":"https://github.com/hymie122.png","language":null,"funding_links":[],"categories":["A01_文本生成_文本对话","Summary","Others","Topics","Key Concepts","🔗 Related Awesome Lists"],"sub_categories":["大语言对话模型及数据","LLM \u0026 RAG","Cost Calculators","General RAG and Agent Frameworks"],"readme":"# Retrieval-Augmented Generation for AI-Generated Content: A Survey\nThis 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.\n\n# Overview\n\u003cdiv aligncenter\u003e\u003cimg width=\"900\" alt=\"image\" src=\"https://github.com/hymie122/RAG-Survey/blob/main/RAG_Overview.jpg\"\u003e\n\n# Catalogue\n## Methods Taxonomy\n### RAG Foundations\n\u003cdiv aligncenter\u003e\u003cimg width=\"900\" alt=\"image\" src=\"https://github.com/hymie122/RAG-Survey/blob/main/RAG_Foundations.png\"\u003e\n\n  - Query-based RAG\n    \n    [REALM: Retrieval-Augmented Language Model Pre-Training](https://arxiv.org/abs/2002.08909)\n    \n    [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://arxiv.org/abs/2310.11511)\n\n    [REPLUG: Retrieval-Augmented Black-Box Language Models](https://arxiv.org/abs/2301.12652)\n\n      [In-Context Retrieval-Augmented Language Models](https://arxiv.org/abs/2302.00083)\n    \n    [When Language Model Meets Private Library](https://arxiv.org/abs/2210.17236)\n    \n    [DocPrompting: Generating Code by Retrieving the Docs](https://openreview.net/pdf?id=ZTCxT2t2Ru)\n\n    [Retrieval-based prompt selection for code-related few-shot learning](https://doi.org/10.1109/ICSE48619.2023.00205)\n\n    [Inferfix: End-to-end program repair with llms](https://doi.org/10.1145/3611643.3613892)\n\n    [Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models](https://proceedings.mlr.press/v202/huang23i.html)\n\n    \n\n    [Reacc: A retrieval-augmented code completion framework](https://doi.org/10.18653/v1/2022.acl-long.431)\n\n\n    [Uni-parser: Unified semantic parser for question answering on knowledge base and database](https://doi.org/10.18653/v1/2022.emnlp-main.605)\n\n\n    [RNG-KBQA: generation augmented iterative ranking for knowledge base question answering](https://doi.org/10.18653/v1/2022.acl-long.417)\n\n    [End-to-end casebased reasoning for commonsense knowledge base completion](https://doi.org/10.18653/v1/2023.eacl-main.255)\n    \n    [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)\n    \n    [Genegpt: Augmenting large language models with domain tools for improved access to biomedical information](https://arxiv.org/abs/2304.09667)\n    \n    [Retrieval-augmented large language models for adolescent idiopathic scoliosis patients in shared decision-making](https://dl.acm.org/doi/10.1145/3584371.3612956)\n    \n    [Retrievegan:Image synthesis via differentiable patch retrieval](https://link.springer.com/chapter/10.1007/978-3-030-58598-3_15)\n    \n    [Instance-conditioned gan](https://proceedings.neurips.cc/paper/2021/file/e7ac288b0f2d41445904d071ba37aaff-Paper.pdf)\n\n\n    [Retrieval-Augmented Score Distillation for Text-to-3D Generation](https://doi.org/10.48550/arXiv.2402.02972)\n    \n  - Latent Representation-based RAG\n\n    [Leveraging passage retrieval with generative models for open domain question answering](https://doi.org/10.18653/v1/2021.eacl-main.74)\n\n\n    [Bashexplainer: Retrieval-augmented bash code comment generation based on finetuned codebert](https://doi.org/10.1109/ICSME55016.2022.00016)\n\n    [EditSum: A Retrieve-and-Edit Framework for Source Code Summarization](https://doi.org/10.1109/ASE51524.2021.9678724)\n\n    [Retrieve and Refine: Exemplar-based Neural Comment Generation](https://arxiv.org/abs/2010.04459)\n    \n    [RACE: retrieval-augmented commit message generation](https://doi.org/10.18653/v1/2022.emnlp-main.372)\n\n    [Unik-qa: Unified representations of structured and unstructured knowledge for open-domain question answering](https://doi.org/10.18653/v1/2022.findings-naacl.115)\n\n    [A Retrieve-and-Edit Framework for Predicting Structured Outputs](https://proceedings.neurips.cc/paper/2018/hash/cd17d3ce3b64f227987cd92cd701cc58-Abstract.html)\n\n    \n\n    [DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases](https://openreview.net/pdf?id=XHc5zRPxqV9)\n\n    [Bridging the kb-text gap: Leveraging structured knowledge-aware pre-training for KBQA](https://doi.org/10.1145/3583780.3615150)\n\n    [Knowledge-driven cot: Exploring faithful reasoning in llms for knowledge-intensive question answering](https://doi.org/10.48550/arXiv.2308.13259)\n\n    [Retrieval-enhanced generative model for large-scale knowledge graph completion](https://doi.org/10.1145/3539618.3592052)\n\n    [Case-based reasoning for natural language queries over knowledge bases](https://doi.org/10.18653/v1/2021)\n\n   \n\n    [A Protein-Ligand Interaction-focused 3D Molecular Generative Framework for Generalizable Structure-based Drug Design](https://chemrxiv.org/engage/chemrxiv/article-details/6482d9dbbe16ad5c57af1937)\n\n    [Improving language models by retrieving from trillions of tokens](https://proceedings.mlr.press/v162/borgeaud22a.html)\n\n    [Remodiffuse: Retrieval-augmented motion diffusion model](https://doi.org/10.1109/ICCV51070.2023.00040)\n\n    [Memorizing transformers](https://openreview.net/forum?id=TrjbxzRcnf-)\n\n    [Audio captioning using pre-trained large-scale language model guided by audio-based similar caption retrieval](https://arxiv.org/abs/2012.07331)\n\n    [Retrieval augmented convolutional encoder-decoder networks for video captioning](https://doi.org/10.1145/3539225)\n\n    [Retrieval-augmented egocentric video captioning](https://doi.org/10.48550/arXiv.2401.00789)\n\n    [Re-imagen: Retrievalaugmented text-to-image generator](https://arxiv.org/abs/2209.14491)\n\n    [Knn-diffusion: Image generation via large-scale retrieval](https://arxiv.org/abs/2204.02849)\n\n    [Retrieval-augmented diffusion models](https://proceedings.neurips.cc/paper_files/paper/2022/file/62868cc2fc1eb5cdf321d05b4b88510c-Paper-Conference.pdf)\n\n    [Text-guided synthesis of artistic images with retrieval-augmented diffusion models](https://arxiv.org/abs/2207.13038)\n    \n\n    [Memory-driven text-to-image generation](https://arxiv.org/abs/2208.07022)\n\n    [Mention memory: incorporating textual knowledge into transformers through entity mention attention](https://arxiv.org/abs/2110.06176)\n\n    [Unlimiformer:Long-range transformers with unlimited length input](https://doi.org/10.48550/arXiv.2305.01625)\n\n    [Entities as experts: Sparse memory access with entity supervision](https://arxiv.org/abs/2004.07202)\n\n    [Amd: Anatomical motion diffusion with interpretable motion decomposition and fusion](https://arxiv.org/abs/2312.12763)\n\n    [Retrieval-augmented text-to-audio generation](https://doi.org/10.48550/arXiv.2309.08051)\n\n    [Concept-aware video captioning: Describing videos with effective prior information](https://doi.org/10.1109/TIP.2023.3307969)\n\n\n\n  - Logit-based RAG\n\n    \n\n    [Generalization through memorization: Nearest neighbor language models](https://openreview.net/forum?id=HklBjCEKvH)\n\n\n\n    [Syntax-Aware Retrieval Augmented Code Generation](https://aclanthology.org/2023.findings-emnlp.90)\n\n    [Memory-augmented image captioning](https://aaai.org/papers/01317-memory-augmented-image-captioning/)\n\n    [Retrieval-based neural source code summarization](https://doi.org/10.1145/3377811.3380383)\n\n    [Efficient nearest neighbor language models](https://doi.org/10.18653/v1/2021.emnlp-main.461)\n\n\n\n    [Nonparametric masked language modeling](https://doi.org/10.18653/v1/2023.findings-acl.132)\n\n    \n\n    [Editsum:A retrieve-and-edit framework for source code summarization](https://doi.org/10.1109/ASE51524.2021.9678724)\n\n\n   \n  - Speculative RAG\n\n    [REST: Retrieval-Based Speculative Decoding](https://doi.org/10.48550/arXiv.2311.08252)\n    \n    [GPTCache](https://github.com/zilliztech/GPTCache)\n\n    [COPY IS ALL YOU NEED](https://arxiv.org/abs/2307.06962)\n\n    [RETRIEVAL IS ACCURATE GENERATION](https://arxiv.org/abs/2402.17532)\n\n### RAG Enhancements\n\u003cdiv aligncenter\u003e\u003cimg width=\"900\" alt=\"image\" src=\"https://github.com/hymie122/RAG-Survey/blob/main/RAG_Enhancements.png\"\u003e\n\n  - Input Enhancement\n    \n    - Query Transformations\n      \n      [Query2doc: Query Expansion with Large Language Models](https://aclanthology.org/2023.emnlp-main.585)\n\n      [Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models](https://openreview.net/forum?id=vDvFT7IX4O)\n\n      [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://doi.org/10.18653/v1/2023.acl-long.99)\n\n      [RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation](https://arxiv.org/pdf/2404.00610)\n\n      [Dynamic Contexts for Generating Suggestion Questions in RAG Based Conversational Systems](https://arxiv.org/pdf/2403.11413)\n      \n    - Data Augmentation\n   \n      [LESS: selecting influential data for targeted instruction tuning](https://arxiv.org/abs/2402.04333)\n\n      [Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models](https://proceedings.mlr.press/v202/huang23i.html)\n\n      [Telco-RAG: Navigating the challenges of retrieval-augmented language models for telecommunications](https://arxiv.org/pdf/2404.15939)\n\n      \n\n  - Retriever Enhancement\n    \n    - Recursive Retrieve\n\n      [Query Expansion by Prompting Large Language Models](https://doi.org/10.48550/arXiv.2305.03653)\n\n      [Rat: Retrieval augmented thoughts elicit context-aware reasoning in long-horizon generation](https://arxiv.org/abs/2403.05313)\n\n      [React: Synergizing reasoning and acting in language models](https://arxiv.org/abs/2210.03629)\n\n      [Chain-of-thought prompting elicits reasoning in large language models](https://arxiv.org/abs/2201.11903)\n\n  \n\n  \n\n      [Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search](https://aclanthology.org/2023.findings-emnlp.86)\n      \n      [ACTIVERAG: Revealing the Treasures of Knowledge via Active Learning](https://arxiv.org/abs/2402.13547)\n\n      [Retrieval-Augmented Thought Process as Sequential Decision Making](https://arxiv.org/abs/2402.07812)\n\n      [In search of needles in a 10m haystack: Recurrent memory finds what llms miss](https://arxiv.org/abs/2402.10790v1)\n      \n      [Lost in the middle: How language models use long contexts](https://arxiv.org/abs/2307.03172)\n\n      \n      \n    - Chunk Optimization\n\n      [LlamaIndex](https://github.com/jerryjliu/llama_index)\n\n      [RAPTOR: RECURSIVE ABSTRACTIVE PROCESSING FOR TREE-ORGANIZED RETRIEVAL](https://arxiv.org/pdf/2401.18059.pdf)\n\n      [Prompt-RAG: Pioneering Vector Embedding-Free Retrieval-Augmented Generation in Niche Domains, Exemplified by Korean Medicine](https://arxiv.org/pdf/2401.11246)\n\n      [Question-Based Retrieval using Atomic Units for Enterprise RAG](https://arxiv.org/pdf/2405.12363)\n      \n    - Finetune Retriever\n\n      [C-Pack: Packaged Resources To Advance General Chinese Embedding](https://arxiv.org/abs/2309.07597)\n\n      [BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://arxiv.org/abs/2402.03216)\n\n      [LM-Cocktail: Resilient Tuning of Language Models via Model Merging](https://arxiv.org/abs/2311.13534)\n\n      [Retrieve Anything To Augment Large Language Models](https://arxiv.org/abs/2310.07554)\n\n      [Replug: Retrieval-augmented black-box language models](https://arxiv.org/abs/2301.12652)\n\n      [When Language Model Meets Private Library](https://doi.org/10.18653/v1/2022.findings-emnlp.21)\n\n      [EditSum: A Retrieve-and-Edit Framework for Source Code Summarization](https://doi.org/10.1109/ASE51524.2021.9678724)\n\n      [Synchromesh: Reliable Code Generation from Pre-trained Language Models](https://openreview.net/forum?id=KmtVD97J43e)\n\n      [Retrieval Augmented Convolutional Encoder-decoder Networks for Video Captioning](https://doi.org/10.1145/3539225)\n\n      [Reinforcement learning for optimizing RAG for domain chatbots](https://arxiv.org/abs/2401.06800)\n   \n    - Hybrid Retrieve\n\n      [RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair](https://doi.org/10.1145/3611643.3616256)\n\n      [ReACC: A Retrieval-Augmented Code Completion Framework](https://doi.org/10.18653/v1/2022.acl-long.431)\n\n      [Retrieval-based neural source code summarization](https://doi.org/10.1145/3377811.3380383)\n\n      [BashExplainer: Retrieval-Augmented Bash Code Comment Generation based on Fine-tuned CodeBERT](https://doi.org/10.1109/ICSME55016.2022.00016)\n\n      [Retrieval-Augmented Score Distillation for Text-to-3D Generation](https://doi.org/10.48550/arXiv.2402.02972)\n\n      [Corrective Retrieval Augmented Generation](https://arxiv.org/abs/2401.15884)\n\n      [Retrieval augmented generation with rich answer encoding](https://aclanthology.org/2023.ijcnlp-main.65.pdf)\n\n      [Unims-rag: A unified multi-source retrieval-augmented generation for personalized dialogue systems](https://arxiv.org/abs/2401.13256)\n\n      [You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval](https://arxiv.org/pdf/2403.07222v1)\n\n      [Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers](https://arxiv.org/pdf/2404.07220)\n   \n    - Re-ranking\n\n      [Re2G: Retrieve, Rerank, Generate](https://doi.org/10.18653/v1/2022.naacl-main.194)\n\n      [Passage Re-ranking with BERT](http://arxiv.org/abs/1901.04085)\n\n      [AceCoder: Utilizing Existing Code to Enhance Code Generation](https://arxiv.org/abs/2303.17780)\n\n      [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)\n\n      [A Fine-tuning Enhanced RAG System with Quantized Influence Measure as AI Judge](https://arxiv.org/abs/2402.17081v1)\n\n      [UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers](https://arxiv.org/pdf/2303.00807.pdf)\n\n      [Learning to Retrieve In-Context Examples for Large Language Models](https://arxiv.org/pdf/2307.07164.pdf)\n\n      [The Chronicles of RAG: The Retriever, the Chunk and the Generator](https://arxiv.org/pdf/2401.07883.pdf)\n\n      [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)\n\n\n\n    - Retrieval Transformation\n\n      [Learning to filter context for retrieval-augmented generation](https://arxiv.org/abs/2311.08377)\n      \n      [Fid-light: Efficient and effective retrieval-augmented text generation](https://arxiv.org/abs/2209.14290)\n      \n      [Gar-meets-rag paradigm for zero-shot information retrieval](https://arxiv.org/abs/2310.20158)\n   \n    - Others\n\n      [PineCone](https://www.pinecone.io)\n    \n      [Generate rather than retrieve: Large language models are strong context generators](https://arxiv.org/abs/2209.10063)\n    \n      [Generator-retriever-generator: A novel approach to open-domain question answering](https://arxiv.org/abs/2307.11278)\n\n      [Multi-Head RAG: Solving Multi-Aspect Problems with LLMs](https://arxiv.org/pdf/2406.05085)\n    \n  - Generator Enhancement\n\n    - Prompt Engineering\n   \n      [Prompt Engineering Guide](https://github.com/dair-ai/Prompt-Engineering-Guide)\n\n      [Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models](https://doi.org/10.48550/arXiv.2310.06117)\n\n      [Active Prompting with Chain-of-Thought for Large Language Models](https://doi.org/10.48550/arXiv.2302.12246)\n\n      [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](http://papers.nips.cc/paper\\_files/paper/2022/hash/9d5609613524ecf4f15af0f7b31abca4-Abstract-Conference.html)\n\n      [LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models](https://aclanthology.org/2023.emnlp-main.825)\n\n      [Lost in the Middle: How Language Models Use Long Contexts](https://doi.org/10.48550/arXiv.2307.03172)\n\n      [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://doi.org/10.1109/ICCV51070.2023.00040)\n\n      [Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)](https://arxiv.org/abs/2304.06815)\n\n      [Retrieval-Based Prompt Selection for Code-Related Few-Shot Learning](https://doi.org/10.1109/ICSE48619.2023.00205)\n\n      [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)\n\n      [Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models](https://proceedings.mlr.press/v202/huang23i.html)\n   \n    - Decoding Tuning\n\n      [InferFix: End-to-End Program Repair with LLMs](https://doi.org/10.1145/3611643.3613892)\n\n      [Synchromesh: Reliable Code Generation from Pre-trained Language Models](https://openreview.net/forum?id=KmtVD97J43e)\n\n   \n    - Finetune Generator\n   \n      [Improving Language Models by Retrieving from Trillions of Tokens](https://proceedings.mlr.press/v162/borgeaud22a.html)\n\n      [When Language Model Meets Private Library](https://doi.org/10.18653/v1/2022.findings-emnlp.21)\n   \n      [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://arxiv.org/abs/2203.13474)\n\n      [Concept-Aware Video Captioning: Describing Videos With Effective Prior Information](https://doi.org/10.1109/TIP.2023.3307969)\n\n      [Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation](https://doi.org/10.48550/arXiv.2307.06940)\n   \n      [Lora: Low-rank adaptation of large language models](https://arxiv.org/abs/2106.09685)\n\n      [Retrieval-Augmented Score Distillation for Text-to-3D Generation](https://doi.org/10.48550/arXiv.2402.02972)\n   \n  - Result Enhancement\n\n    - Rewrite Output\n   \n      [Automated Code Editing with Search-Generate-Modify](https://doi.org/10.48550/arXiv.2306.06490)\n\n      [Repair Is Nearly Generation: Multilingual Program Repair with LLMs](https://doi.org/10.1609/aaai.v37i4.25642)\n\n      [Case-based Reasoning for Natural Language Queries over Knowledge Bases](https://doi.org/10.18653/v1/2021.emnlp-main.755)\n\n  - RAG Pipeline Enhancement\n    \n    - Adaptive Retrieval\n      \n      - Rule-Baesd\n     \n        [Active retrieval augmented generation](https://arxiv.org/abs/2305.06983)\n\n        [Efficient Nearest Neighbor Language Models](https://doi.org/10.18653/v1/2021.emnlp-main.461)\n\n        [Generalization through Memorization: Nearest Neighbor Language Models](https://arxiv.org/abs/1911.00172)\n\n        [Nonparametric masked language modeling](https://arxiv.org/abs/2212.01349)\n\n        [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://doi.org/10.18653/v1/2023.acl-long.546)\n\n        [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)\n\n        [Large Language Models Struggle to Learn Long-Tail Knowledge](https://proceedings.mlr.press/v202/kandpal23a.html)\n    \n      - Model-Based\n        \n        [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://doi.org/10.48550/arXiv.2310.11511)\n\n        [Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation](https://doi.org/10.48550/arXiv.2307.11019)\n\n        [Self-Knowledge Guided Retrieval Augmentation for Large Language Models](https://aclanthology.org/2023.findings-emnlp.691)\n     \n        [Retrieve only when it needs: Adaptive retrieval augmentation for hallucination mitigation in large language models](https://arxiv.org/abs/2402.10612)\n\n        [Adaptive-rag: Learning to adapt retrieval-augmented large language models through question complexity](https://arxiv.org/abs/2403.14403)\n   \n    - Iterative RAG\n   \n      [RepoCoder: Repository-Level  Through Iterative Retrieval and Generation](https://aclanthology.org/2023.emnlp-main.151)\n\n      [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://aclanthology.org/2023.findings-emnlp.620)\n    \n      [Knowledge graph based synthetic corpus generation for knowledge-enhanced language model pre-training](https://arxiv.org/abs/2010.12688)\n\n\n## Applications Taxonomy\n\u003cdiv aligncenter\u003e\u003cimg width=\"900\" alt=\"image\" src=\"https://github.com/hymie122/RAG-Survey/blob/main/Applications.png\"\u003e\n\u003cdiv aligncenter\u003e\u003cimg width=\"900\" alt=\"image\" src=\"https://github.com/hymie122/RAG-Survey/blob/main/RAG_Applications.png\"\u003e\n  \n### RAG for Text\n  - Question Answering\n\n    [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://doi.org/10.18653/v1/2021.eacl-main.74)\n\n    [REALM: Retrieval-Augmented Language Model Pre-Training](https://arxiv.org/abs/2002.08909)\n\n    [Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training](https://doi.org/10.18653/v1/2021.naacl-main.278)\n\n    [Atlas: Few-shot Learning with Retrieval Augmented Language Models](http://jmlr.org/papers/v24/23-0037.html)\n\n    [Improving Language Models by Retrieving from Trillions of Tokens](https://proceedings.mlr.press/v162/borgeaud22a.html)\n\n    [Self-Knowledge Guided Retrieval Augmentation for Large Language Models](https://aclanthology.org/2023.findings-emnlp.691)\n\n    [Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering](https://doi.org/10.48550/arXiv.2306.04136)\n\n    [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model with Knowledge Graph](https://doi.org/10.48550/arXiv.2307.07697)\n\n    [Nonparametric Masked Language Modeling](https://doi.org/10.18653/v1/2023.findings-acl.132)\n\n    [CL-ReLKT: Cross-lingual Language Knowledge Transfer for Multilingual Retrieval Question Answering](https://doi.org/10.18653/v1/2022.findings-naacl.165)\n\n    [One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval](https://proceedings.neurips.cc/paper/2021/hash/3df07fdae1ab273a967aaa1d355b8bb6-Abstract.html)\n\n    [Entities as Experts: Sparse Memory Access with Entity Supervision](https://arxiv.org/abs/2004.07202)\n\n    [When to Read Documents or QA History: On Unified and Selective Open-domain QA](https://doi.org/10.18653/v1/2023.findings-acl.401)\n\n    [Enhancing LLM Intelligence with ARM-RAG: Auxiliary Rationale Memory for Retrieval Augmented Generation](https://arxiv.org/abs/2311.04177)\n\n    [DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Service](https://arxiv.org/pdf/2309.11325.pdf)\n\n  - Fact verification\n\n    [CONCRETE: Improving Cross-lingual Fact-checking with Cross-lingual Retrieval](https://aclanthology.org/2022.coling-1.86)\n\n    [Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization](https://arxiv.org/pdf/2405.02816)\n\n  - Commonsense Reasoning\n\n    [KG-BART: Knowledge Graph-Augmented {BART} for Generative Commonsense Reasoning](https://doi.org/10.1609/aaai.v35i7.16796)\n\n    [What Evidence Do Language Models Find Convincing?](https://arxiv.org/abs/2402.11782v1)\n\n    [Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models](https://arxiv.org/abs/2310.04027)\n\n  - Human-Machine Conversation\n\n    [Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs](https://doi.org/10.18653/v1/2020.acl-main.184)\n\n    [Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory](https://doi.org/10.18653/v1/n19-1124)\n\n    [Internet-Augmented Dialogue Generation](https://doi.org/10.18653/v1/2022.acl-long.579)\n\n    [BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage](https://doi.org/10.48550/arXiv.2208.03188)\n\n    [A Model of Cross-Lingual Knowledge-Grounded Response Generation for Open-Domain Dialogue Systems](https://doi.org/10.18653/v1/2021.findings-emnlp.33)\n\n    [From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICL](https://openreview.net/forum?id=KLPLCXo4aD)\n\n    [Cross-Lingual Retrieval Augmented Prompt for Low-Resource Languages](https://aclanthology.org/2023.findings-acl.528/)\n\n    [Citation-Enhanced Generation for LLM-based Chatbot](https://arxiv.org/pdf/2402.16063v1.pdf)\n\n    [KAUCUS: Knowledge Augmented User Simulators for Training Language Model Assistants](https://aclanthology.org/2024.scichat-1.5/)\n\n    \n\n  - Neural Machine Translation\n\n    [Neural Machine Translation with Monolingual Translation Memory](https://doi.org/10.18653/v1/2021.acl-long.567)\n\n    [Nearest Neighbor Machine Translation](https://openreview.net/forum?id=7wCBOfJ8hJM)\n\n    [Training Language Models with Memory Augmentation](https://doi.org/10.18653/v1/2022.emnlp-main.382)\n\n  - Event Extraction\n\n    [Retrieval-Augmented Generative Question Answering for Event Argument Extraction](https://doi.org/10.18653/v1/2022.emnlp-main.307)\n\n  - Summarization\n\n    [Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training](https://doi.org/10.18653/v1/2022.findings-naacl.92)\n\n    [Unlimiformer: Long-Range Transformers with Unlimited Length Input](https://doi.org/10.48550/arXiv.2305.01625)\n    \n    [Retrieval-based Full-length Wikipedia Generation for Emergent Events](https://arxiv.org/abs/2402.18264v1)\n\n    [RIGHT: Retrieval-augmented Generation for Mainstream Hashtag Recommendation](https://arxiv.org/abs/2312.10466)\n\n    [M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions](https://arxiv.org/pdf/2405.16420)\n\n### RAG for Code\n  - Code Generation\n\n    [Retrieval-Based Neural Code Generation](https://doi.org/10.18653/v1/d18-1111)\n\n    [Retrieval Augmented Code Generation and Summarization](https://doi.org/10.18653/v1/2021.findings-emnlp.232)\n\n    [When Language Model Meets Private Library](https://doi.org/10.18653/v1/2022.findings-emnlp.21)\n\n    [Language Models of Code are Few-Shot Commonsense Learners](https://doi.org/10.18653/v1/2022.emnlp-main.90)\n\n    [DocPrompting: Generating Code by Retrieving the Docs](https://openreview.net/pdf?id=ZTCxT2t2Ru)\n\n    [CodeT5+: Open Code Large Language Models for Code Understanding and Generation](https://aclanthology.org/2023.emnlp-main.68)\n\n    [AceCoder: Utilizing Existing Code to Enhance Code Generation](https://arxiv.org/abs/2303.17780)\n\n    [Syntax-Aware Retrieval Augmented Code Generation](https://aclanthology.org/2023.findings-emnlp.90)\n\n    [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)\n\n    [SkCoder: A Sketch-based Approach for Automatic Code Generation](https://ieeexplore.ieee.org/abstract/document/10172719)\n\n    [CodeGen4Libs: A Two-Stage Approach for Library-Oriented Code Generation](https://ieeexplore.ieee.org/abstract/document/10298327)\n\n    [ToolCoder: Teach Code Generation Models to use API search tools](https://arxiv.org/abs/2305.04032)\n\n    [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://arxiv.org/abs/2401.07339)\n\n    [RRGcode: Deep hierarchical search-based code generation](https://www.sciencedirect.com/science/article/pii/S0164121224000256)\n\n    [Code Search Is All You Need? Improving Code Suggestions with Code Search](https://www.computer.org/csdl/proceedings-article/icse/2024/021700a857/1V5BkjI3196)\n\n    [ARKS: Active Retrieval in Knowledge Soup for Code Generation](https://arxiv.org/abs/2402.12317)\n\n  - Code Summary\n\n    [Retrieval-based neural source code summarization](https://doi.org/10.1145/3377811.3380383)\n\n    [Retrieve and Refine: Exemplar-based Neural Comment Generation](https://doi.org/10.1145/3324884.3416578)\n\n    [EditSum: A Retrieve-and-Edit Framework for Source Code Summarization](https://doi.org/10.1109/ASE51524.2021.9678724)\n\n    [Retrieval-Augmented Generation for Code Summarization via Hybrid GNN](https://openreview.net/forum?id=zv-typ1gPxA)\n\n    [Context-aware Retrieval-based Deep Commit Message Generation](https://dl.acm.org/doi/abs/10.1145/3464689)\n\n    [RACE: Retrieval-augmented Commit Message Generation](https://doi.org/10.18653/v1/2022.emnlp-main.372)\n\n    [BashExplainer: Retrieval-Augmented Bash Code Comment Generation based on Fine-tuned CodeBERT](https://doi.org/10.1109/ICSME55016.2022.00016)\n\n    [Retrieval-Based Transformer Pseudocode Generation](https://www.mdpi.com/2227-7390/10/4/604)\n\n    [A Simple Retrieval-based Method for Code Comment Generation](https://ieeexplore.ieee.org/abstract/document/9825803)\n\n    [READSUM: Retrieval-Augmented Adaptive Transformer for Source Code Summarization](https://ieeexplore.ieee.org/abstract/document/10113620)\n\n    [Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization](https://arxiv.org/abs/2305.11074)\n\n    [Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)](https://arxiv.org/abs/2304.06815)\n\n    [Cross-Modal Retrieval-Enhanced Code Summarization based on Joint Learning for Retrieval and Generation](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4724884)\n\n    [Automatic Smart Contract Comment Generation via Large Language Models and In-Context Learning](https://www.sciencedirect.com/science/article/pii/S0950584924000107)\n\n    [UniLog: Automatic Logging via LLM and In-Context Learning](https://dl.acm.org/doi/abs/10.1145/3597503.3623326)\n\n  - Code Completion\n\n    [A Retrieve-and-Edit Framework for Predicting Structured Outputs](https://proceedings.neurips.cc/paper_files/paper/2018/hash/cd17d3ce3b64f227987cd92cd701cc58-Abstract.html)\n\n    [Generating Code with the Help of Retrieved Template Functions and Stack Overflow Answers](https://arxiv.org/abs/2104.05310)\n\n    [ReACC: A Retrieval-Augmented Code Completion Framework](https://doi.org/10.18653/v1/2022.acl-long.431)\n\n    [Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases](https://ieeexplore.ieee.org/abstract/document/10298575)\n\n    [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://aclanthology.org/2023.emnlp-main.151)\n\n    [CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context](https://doi.org/10.48550/arXiv.2212.10007)\n\n    [RepoFusion: Training Code Models to Understand Your Repository](https://arxiv.org/abs/2306.10998)\n\n    [Revisiting and Improving Retrieval-Augmented Deep Assertion Generation](https://ieeexplore.ieee.org/abstract/document/10298588)\n\n    [De-Hallucinator: Iterative Grounding for LLM-Based Code Completion](https://arxiv.org/abs/2401.01701)\n\n    [REPOFUSE: Repository-Level Code Completion with Fused Dual Context](https://arxiv.org/abs/2402.14323)\n\n  - Automatic Program Repair\n\n    [Repair Is Nearly Generation: Multilingual Program Repair with LLMs](https://doi.org/10.1609/aaai.v37i4.25642)\n\n    [Retrieval-Based Prompt Selection for Code-Related Few-Shot Learning](https://doi.org/10.1109/ICSE48619.2023.00205)\n\n    [InferFix: End-to-End Program Repair with LLMs](https://doi.org/10.1145/3611643.3613892)\n\n    [RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair](https://dl.acm.org/doi/abs/10.1145/3611643.3616256)\n\n    [Automated Code Editing with Search-Generate-Modify](https://arxiv.org/abs/2306.06490)\n\n    [RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Models](https://arxiv.org/abs/2311.16543)\n\n  - Text-to-SQL and Code-based Semantic Parsing\n\n    [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)\n\n    [Synchromesh: Reliable Code Generation from Pre-trained Language Models](https://openreview.net/forum?id=KmtVD97J43e)\n\n    [Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing](https://aclanthology.org/2022.emnlp-main.624/)\n\n    [RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL](https://ojs.aaai.org/index.php/AAAI/article/view/26535)\n\n    [Leveraging Code to Improve In-context Learning for Semantic Parsing](https://arxiv.org/abs/2311.09519)\n\n    [ReFSQL: A Retrieval-Augmentation Framework for Text-to-SQL Generation](https://aclanthology.org/2023.findings-emnlp.48/)\n\n    [Enhancing Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies](https://aclanthology.org/2023.findings-emnlp.996/)\n\n    [Selective Demonstrations for Cross-domain Text-to-SQL](https://aclanthology.org/2023.findings-emnlp.944/)\n\n    [DBCopilot: Scaling Natural Language Querying to Massive Databases via Schema Routing](https://arxiv.org/abs/2312.03463)\n\n    [Multi-Hop Table Retrieval for Open-Domain Text-to-SQL](https://arxiv.org/abs/2402.10666)\n\n    [CodeS: Towards Building Open-source Language Models for Text-to-SQL](https://arxiv.org/abs/2402.16347)\n\n  - Others\n\n    [De-fine: Decomposing and Refining Visual Programs with Auto-Feedback](https://arxiv.org/abs/2311.12890)\n\n    [Leveraging training data in few-shot prompting for numerical reasoning](https://arxiv.org/abs/2305.18170)\n\n    [Retrieval-Augmented Code Generation for Universal Information Extraction](https://arxiv.org/abs/2311.02962)\n\n    [E\u0026V: Prompting Large Language Models to Perform Static Analysis by Pseudo-code Execution and Verification](https://arxiv.org/abs/2312.08477)\n\n    [Lessons from Building StackSpot AI: A Contextualized AI Coding Assistant](https://arxiv.org/abs/2311.18450)\n\n    [Testing the Limits: Unusual Text Inputs Generation for Mobile App Crash Detection with Large Language Model](https://arxiv.org/abs/2310.15657)\n\n### RAG for Audio\n  - Audio Generation\n\n    [Retrieval-Augmented Text-to-Audio Generation](https://doi.org/10.48550/arXiv.2309.08051)\n\n    [Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://doi.org/10.1109/ICASSP49357.2023.10095969)\n\n    [Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models](https://proceedings.mlr.press/v202/huang23i.html)\n\n  - Audio Captioning\n\n    [RECAP: Retrieval-Augmented Audio Captioning](https://doi.org/10.48550/arXiv.2309.09836)\n\n    [Audio Captioning using Pre-Trained Large-Scale Language Model Guided by Audio-based Similar Caption Retrieval](https://arxiv.org/abs/2012.07331)\n\n    [Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://doi.org/10.1109/ICASSP49357.2023.10095969)\n\n    [CNN architectures for large-scale audio classification](https://doi.org/10.1109/ICASSP.2017.7952132)\n\n    [Natural language supervision for general-purpose audio representations](https://ieeexplore.ieee.org/abstract/document/10448504)\n\n    [Weakly-supervised Automated Audio Captioning via text only training](https://arxiv.org/abs/2309.12242)\n\n    [Training Audio Captioning Models without Audio](https://ieeexplore.ieee.org/abstract/document/10448115)\n\n### RAG for Image\n  - Image Generation\n\n    [Retrievegan: Image synthesis via differentiable patch retrieval](https://arxiv.org/abs/2007.08513)\n\n    [Instance-conditioned gan](https://arxiv.org/abs/2109.05070)\n\n    [Memory-driven text-to-image generation](https://arxiv.org/abs/2208.07022)\n\n    [Re-imagen: Retrieval-augmented text-to-image generator](https://arxiv.org/abs/2209.14491)\n\n    [KNN-Diffusion: Image Generation via Large-Scale Retrieval](https://arxiv.org/abs/2204.02849)\n\n    [Retrieval-Augmented Diffusion Models](https://arxiv.org/abs/2204.11824)\n\n    [Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models](https://arxiv.org/abs/2207.13038)\n\n    [X\u0026Fuse: Fusing Visual Information in Text-to-Image Generation](https://arxiv.org/abs/2303.01000)\n\n    [Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs](https://arxiv.org/abs/2401.11708)\n\n  - Image Captioning\n\n    [Memory-augmented image captioning](https://ojs.aaai.org/index.php/AAAI/article/view/16220)\n\n    [Retrieval-enhanced adversarial training with dynamic memory-augmented attention for image paragraph captioning](https://www.sciencedirect.com/science/article/pii/S0950705120308595)\n\n    [Retrieval-Augmented Transformer for Image Captioning](https://arxiv.org/abs/2207.13162)\n\n    [Retrieval-augmented image captioning](https://arxiv.org/abs/2302.08268)\n\n    [Reveal: Retrieval-augmented visual-language pre-training with multi-source multimodal knowledge memory](https://arxiv.org/abs/2212.05221)\n\n    [SmallCap: Lightweight Image Captioning Prompted With Retrieval Augmentation](https://arxiv.org/abs/2209.15323)\n\n    [Cross-Modal Retrieval and Semantic Refinement for Remote Sensing Image Captioning](https://www.mdpi.com/2072-4292/16/1/196)\n\n  - Others\n        \n    [An empirical study of gpt-3 for few-shot knowledge-based vqa](https://ojs.aaai.org/index.php/AAAI/article/view/20215)\n    \n    [Retrieval augmented visual question answering with outside knowledge](https://aclanthology.org/2022.emnlp-main.772/)\n    \n    [Augmenting transformers with KNN-based composite memory for dialog](https://doi.org/10.1162/tacl_a_00356)\n    \n    [Maria: A visual experience powered conversational agent](https://aclanthology.org/2021.acl-long.435/)\n    \n    [Neural machine translation with phrase-level universal visual representations](https://aclanthology.org/2022.acl-long.390/)\n\n\n### RAG for Video\n  - Video Captioning\n\n    [Incorporating Background Knowledge into Video Description Generation](https://aclanthology.org/D18-1433/)\n\n    [Retrieval Augmented Convolutional Encoder-decoder Networks for Video Captioning](https://doi.org/10.1145/3539225)\n\n    [Concept-Aware Video Captioning: Describing Videos With Effective Prior Information](https://doi.org/10.1109/TIP.2023.3307969)\n\n    [Retrieval-Augmented Egocentric Video Captioning](https://arxiv.org/abs/2401.00789)\n\n  - Video QA\u0026Dialogue\n\n    [Memory augmented deep recurrent neural network for video question answering](https://doi.org/10.1109/TNNLS.2019.2938015)\n\n    [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)\n\n    [Tvqa+: Spatio-temporal grounding for video question answering](https://aclanthology.org/2020.acl-main.730/)\n\n    [Vgnmn: Video-grounded neural module networks for video-grounded dialogue systems](https://aclanthology.org/2022.naacl-main.247/)\n\n  - Others\n\n    [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)\n    \n    [RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model](https://arxiv.org/abs/2402.10828)\n\n    [Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation](https://doi.org/10.48550/arXiv.2307.06940)\n\n    [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://doi.org/10.1109/ICCV48922.2021.00175)\n\n### RAG for 3D\n  - Text-to-3D\n\n    [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://doi.org/10.1109/ICCV51070.2023.00040)\n\n    [AMD: Anatomical Motion Diffusion with Interpretable Motion Decomposition and Fusion](https://arxiv.org/abs/2312.12763)\n\n    [Retrieval-Augmented Score Distillation for Text-to-3D Generation](https://doi.org/10.48550/arXiv.2402.02972)\n\n### RAG for Knowledge\n  - Knowledge Base Question Answering\n\n    [ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering](https://doi.org/10.18653/v1/2021.acl-demo.39)\n\n    [Unseen Entity Handling in Complex Question Answering over Knowledge Base via Language Generation](https://aclanthology.org/2021.findings-emnlp.50/)\n\n    [Case-based Reasoning for Natural Language Queries over Knowledge Bases](https://doi.org/10.18653/v1/2021.emnlp-main.755)\n\n    [Logical Form Generation via Multi-task Learning for Complex Question Answering over Knowledge Bases](https://aclanthology.org/2022.coling-1.145)\n\n    [Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database](https://aclanthology.org/2022.emnlp-main.605/)\n\n    [RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering](https://aclanthology.org/2022.acl-long.417/)\n\n    [TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Base](https://aclanthology.org/2022.emnlp-main.555/)\n\n    [DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases](https://openreview.net/forum?id=XHc5zRPxqV9)\n\n    [End-to-end Case-Based Reasoning for Commonsense Knowledge Base Completion](https://aclanthology.org/2023.eacl-main.255/)\n\n    [Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA](https://dl.acm.org/doi/abs/10.1145/3583780.3615150)\n\n    [Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering](https://arxiv.org/abs/2308.13259)\n\n    [Few-shot Transfer Learning for Knowledge Base Question Answering: Fusing Supervised Models with In-Context Learning](https://arxiv.org/abs/2311.08894)\n\n    [FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering](https://aclanthology.org/2023.acl-long.57/)\n\n    [Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering](https://aclanthology.org/2023.nlrse-1.7/)\n\n    [Knowledge Graph-augmented Language Models for Complex Question Answering](https://aclanthology.org/2023.nlrse-1.1/)\n\n    [Retrieve-Rewrite-Answer: A KG-to-Text Enhanced LLMs Framework for Knowledge Graph Question Answering](https://arxiv.org/abs/2309.11206)\n\n    [Distribution Shifts Are Bottlenecks: Extensive Evaluation for Grounding Language Models to Knowledge Bases](https://aclanthology.org/2024.eacl-srw.7/)\n\n    [Probing Structured Semantics Understanding and Generation of Language Models via Question Answering](https://arxiv.org/abs/2401.05777)\n\n    [Keqing: Knowledge-based Question Answering is A Nature Chain-of-Thought mentor of LLMs](https://arxiv.org/abs/2401.00426)\n\n    [Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models](https://arxiv.org/abs/2402.15131)\n\n  - Knowledge-augmented Open-domain Question Answering\n\n    [UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering](https://aclanthology.org/2022.findings-naacl.115/)\n\n    [KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering](https://aclanthology.org/2022.acl-long.340/)\n\n    [Empowering Language Models with Knowledge Graph Reasoning for Open-Domain Question Answering](https://aclanthology.org/2022.emnlp-main.650/)\n\n    [Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering](https://aclanthology.org/2022.findings-emnlp.13/)\n\n    [Enhancing Multi-modal Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation](https://dl.acm.org/doi/abs/10.1145/3581783.3611964)\n\n    [DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text](https://arxiv.org/abs/2310.20170)\n\n    [KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases](https://arxiv.org/abs/2308.11761)\n\n    [Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering](https://arxiv.org/abs/2403.02966)\n\n    [Two-stage Generative Question Answering on Temporal Knowledge Graph Using Large Language Models](https://arxiv.org/abs/2402.16568)\n\n    [KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph](https://arxiv.org/abs/2312.15880)\n\n    [GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning](https://arxiv.org/pdf/2405.20139)\n\n  - Table Question Answering\n\n    [NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned](https://proceedings.mlr.press/v133/min21a.html)\n\n    [Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering](https://aclanthology.org/2021.acl-long.315/)\n\n    [End-to-End Table Question Answering via Retrieval-Augmented Generation](https://arxiv.org/abs/2203.16714)\n\n    [OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering](https://aclanthology.org/2022.naacl-main.68/)\n\n    [Reasoning over Hybrid Chain for Table-and-Text Open Domain Question Answering](https://www.ijcai.org/proceedings/2022/0629.pdf)\n\n    [Conversational Question Answering on Heterogeneous Sources](https://dl.acm.org/doi/abs/10.1145/3477495.3531815)\n\n    [Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge](https://aclanthology.org/2022.findings-emnlp.392/)\n\n    [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://aclanthology.org/2023.emnlp-main.574/)\n\n    [cTBLS: Augmenting Large Language Models with Conversational Tables](https://aclanthology.org/2023.nlp4convai-1.6/)\n\n    [RINK: Reader-Inherited Evidence Reranker for Table-and-Text Open Domain Question Answering](https://ojs.aaai.org/index.php/AAAI/article/view/26577)\n\n    [Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables](https://aclanthology.org/2023.findings-ijcnlp.1/)\n\n    [Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid Data](https://arxiv.org/abs/2402.12869)\n\n    [ERATTA: Extreme RAG for Table To Answers with Large Language Models](https://arxiv.org/pdf/2405.03963)\n\n  - Others\n\n    [Improving Knowledge-Aware Dialogue Response Generation by Using Human-Written Prototype Dialogues](https://aclanthology.org/2020.findings-emnlp.126/)\n\n    [Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation](https://arxiv.org/abs/2305.18846)\n\n    [RHO: Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding](https://aclanthology.org/2023.findings-acl.275/)\n\n    [Retrieval-Enhanced Generative Model for Large-Scale Knowledge Graph Completion](https://doi.org/10.1145/3539618.3592052)\n\n    [Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestion](https://arxiv.org/abs/2311.06318)\n\n    [G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering](https://arxiv.org/abs/2402.07630)\n\n    [RAG-based Explainable Prediction of Road Users Behaviors for Automated Driving using Knowledge Graphs and Large Language Models](https://arxiv.org/pdf/2405.00449)\n\n    [HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models](https://arxiv.org/pdf/2405.14831)\n\n### RAG for Science\n  - Drug Discovery\n    \n    [Retrieval-based controllable molecule generation](https://arxiv.org/abs/2208.11126)\n    \n    [Prompt-based 3d molecular diffusion models for structure-based drug design](https://openreview.net/forum?id=FWsGuAFn3n)\n    \n  - Biomedical Informatics Enhancement\n\n    [PoET: A generative model of protein families as sequences-of-sequences](https://proceedings.neurips.cc/paper_files/paper/2023/hash/f4366126eba252699b280e8f93c0ab2f-Abstract-Conference.html)\n    \n    [Retrieval-augmented large language models for adolescent idiopathic scoliosis patients in shared decision-making](https://dl.acm.org/doi/abs/10.1145/3584371.3612956)\n\n    [BioReader: a Retrieval-Enhanced Text-to-Text Transformer for Biomedical Literature](https://aclanthology.org/2022.emnlp-main.390/)\n\n    [Writing by Memorizing: Hierarchical Retrieval-based Medical Report Generation](https://arxiv.org/abs/2106.06471)\n\n    [From RAG to QA-RAG: Integrating Generative AI for Pharmaceutical Regulatory Compliance Process](https://arxiv.org/abs/2402.01717)\n\n    [RAG-RLRC-LaySum at BioLaySumm: Integrating Retrieval-Augmented Generation and Readability Control for Layman Summarization of Biomedical Texts](https://arxiv.org/pdf/2405.13179)\n\n  - Math Applications\n\n    [Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference](https://arxiv.org/abs/2310.03184)\n\n    [LeanDojo: Theorem Proving with Retrieval-Augmented Language Models](https://proceedings.neurips.cc/paper_files/paper/2023/hash/4441469427094f8873d0fecb0c4e1cee-Abstract-Datasets_and_Benchmarks.html)\n\n## Benchmark\n  [Benchmarking Large Language Models in Retrieval-Augmented Generation](https://doi.org/10.48550/arXiv.2309.01431)\n  \n  [CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models](https://doi.org/10.48550/arXiv.2401.17043)\n  \n  [ARES: An Automated Evaluation Framework for Retrieval-AugmentedGeneration Systems](https://doi.org/10.48550/arXiv.2311.09476)\n  \n  [RAGAS: Automated Evaluation of Retrieval Augmented Generation](https://doi.org/10.48550/arXiv.2309.15217)\n\n  [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://arxiv.org/abs/2009.02252)\n\n\n## Citation\nif you find this work useful, please cite our paper:\n```\n@article{zhao2024retrieval,\n  title={Retrieval-Augmented Generation for AI-Generated Content: A Survey},\n  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},\n  journal={arXiv preprint arXiv:2402.19473},\n  year={2024}\n}\n```\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhymie122%2FRAG-Survey","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhymie122%2FRAG-Survey","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhymie122%2FRAG-Survey/lists"}