{"url":"/task/retrieval-augmented-generation","name":"Retrieval-augmented Generation","slug":"retrieval-augmented-generation","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":2196,"papers_with_code":777,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":777,"tagged_in_all":2196,"items":[{"url":"/paper/retrieval-augmented-generation-for-knowledge","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","date":"2020-05-22","arxiv_id":"2005.11401","repositories_listed":18,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/self-rag-learning-to-retrieve-generate-and","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","date":"2023-10-17","arxiv_id":"2310.11511","repositories_listed":6,"syntology":{"n":14,"n_ran":8,"n_unverified":6,"n_pointer_only":3}},{"url":"/paper/colpali-efficient-document-retrieval-with","title":"ColPali: Efficient Document Retrieval with Vision Language Models","date":"2024-06-27","arxiv_id":"2407.01449","repositories_listed":5,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/babilong-testing-the-limits-of-llms-with-long","title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","date":"2024-06-14","arxiv_id":"2406.10149","repositories_listed":4,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/retrieval-augmented-generation-for-large","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","date":"2023-12-18","arxiv_id":"2312.10997","repositories_listed":4,"syntology":null},{"url":"/paper/simpledeepsearcher-deep-information-seeking","title":"SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis","date":"2025-05-22","arxiv_id":"2505.16834","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/r1-searcher-incentivizing-the-dynamic","title":"R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning","date":"2025-05-22","arxiv_id":"2505.17005","repositories_listed":3,"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/lrp4rag-detecting-hallucinations-in-retrieval","title":"LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagation","date":"2024-08-28","arxiv_id":"2408.15533","repositories_listed":3,"syntology":null},{"url":"/paper/from-local-to-global-a-graph-rag-approach-to","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","date":"2024-04-24","arxiv_id":"2404.16130","repositories_listed":3,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/retrieval-augmented-generation-for-ai","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","date":"2024-02-29","arxiv_id":"2402.19473","repositories_listed":3,"syntology":null},{"url":"/paper/the-power-of-noise-redefining-retrieval-for","title":"The Power of Noise: Redefining Retrieval for RAG Systems","date":"2024-01-26","arxiv_id":"2401.14887","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/ragtruth-a-hallucination-corpus-for","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","date":"2023-12-31","arxiv_id":"2401.00396","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/ragas-automated-evaluation-of-retrieval","title":"RAGAS: Automated Evaluation of Retrieval Augmented Generation","date":"2023-09-26","arxiv_id":"2309.15217","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/a-survey-of-llm-times-data","title":"A Survey of LLM $\\times$ DATA","date":"2025-05-24","arxiv_id":"2505.18458","repositories_listed":2,"syntology":null},{"url":"/paper/relevance-isn-t-all-you-need-scaling-rag","title":"Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria Reranking","date":"2025-03-14","arxiv_id":"2504.07104","repositories_listed":2,"syntology":null},{"url":"/paper/huixiangdou2-a-robustly-optimized-graphrag","title":"HuixiangDou2: A Robustly Optimized GraphRAG Approach","date":"2025-03-09","arxiv_id":"2503.06474","repositories_listed":2,"syntology":null},{"url":"/paper/benchmarking-retrieval-augmented-generation-1","title":"Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts","date":"2025-02-24","arxiv_id":"2502.17297","repositories_listed":2,"syntology":null},{"url":"/paper/lettucedetect-a-hallucination-detection","title":"LettuceDetect: A Hallucination Detection Framework for RAG Applications","date":"2025-02-24","arxiv_id":"2502.17125","repositories_listed":2,"syntology":null},{"url":"/paper/ras-retrieval-and-structuring-for-knowledge","title":"RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation","date":"2025-02-16","arxiv_id":"2502.10996","repositories_listed":2,"syntology":{"n":13,"n_ran":1,"n_unverified":12,"n_pointer_only":2}},{"url":"/paper/autoagent-a-fully-automated-and-zero-code","title":"AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents","date":"2025-02-09","arxiv_id":"2502.05957","repositories_listed":2,"syntology":null},{"url":"/paper/webwalker-benchmarking-llms-in-web-traversal","title":"WebWalker: Benchmarking LLMs in Web Traversal","date":"2025-01-13","arxiv_id":"2501.07572","repositories_listed":2,"syntology":null},{"url":"/paper/search-o1-agentic-search-enhanced-large","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","date":"2025-01-09","arxiv_id":"2501.05366","repositories_listed":2,"syntology":null},{"url":"/paper/jasper-and-stella-distillation-of-sota","title":"Jasper and Stella: distillation of SOTA embedding models","date":"2024-12-26","arxiv_id":"2412.19048","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/conqret-benchmarking-fine-grained-evaluation","title":"ConQRet: Benchmarking Fine-Grained Evaluation of Retrieval Augmented Argumentation with LLM Judges","date":"2024-12-06","arxiv_id":"2412.05206","repositories_listed":2,"syntology":null},{"url":"/paper/initial-nugget-evaluation-results-for-the","title":"Initial Nugget Evaluation Results for the TREC 2024 RAG Track with the AutoNuggetizer Framework","date":"2024-11-14","arxiv_id":"2411.09607","repositories_listed":2,"syntology":null},{"url":"/paper/autorag-automated-framework-for-optimization","title":"AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation Pipeline","date":"2024-10-28","arxiv_id":"2410.20878","repositories_listed":2,"syntology":null},{"url":"/paper/lorann-low-rank-matrix-factorization-for","title":"LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search","date":"2024-10-24","arxiv_id":"2410.18926","repositories_listed":2,"syntology":{"n":20,"n_ran":0,"n_unverified":20,"n_pointer_only":0}},{"url":"/paper/faithbench-a-diverse-hallucination-benchmark","title":"FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs","date":"2024-10-17","arxiv_id":"2410.13210","repositories_listed":2,"syntology":null},{"url":"/paper/colacare-enhancing-electronic-health-record","title":"ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration","date":"2024-10-03","arxiv_id":"2410.02551","repositories_listed":2,"syntology":null},{"url":"/paper/data-prep-kit-getting-your-data-ready-for-llm","title":"Data-Prep-Kit: getting your data ready for LLM application development","date":"2024-09-26","arxiv_id":"2409.18164","repositories_listed":2,"syntology":null}],"syntology_records":13,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}