{"url":"/method/rag","slug":"rag","name":"RAG","full_name":"RAG","full_name_withheld":false,"description_markdown":"**Retriever-Augmented Generation**, or **RAG**, is a type of language generation model that combines pre-trained parametric and non-parametric memory for language generation. Specifically, the parametric memory is a pre-trained seq2seq model and the non-parametric memory is a dense vector index of Wikipedia, accessed with a pre-trained neural retriever.  For query $x$, Maximum Inner Product Search (MIPS) is used to find the top-K documents $z\\_{i}$. For final prediction $y$, we treat $z$ as a latent variable and marginalize over seq2seq predictions given different documents.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","paper":"/paper/retrieval-augmented-generation-for-knowledge","first_author":"Patrick Lewis","n_authors":12,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/retrieval-augmented-generation-for-knowledge"},"source":{"url":"https://arxiv.org/abs/2005.11401v4","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Transformers","url":"/methods/category/transformers","pwc_aliases":[]}],"n_papers_tagged":1286,"archive_num_papers":1286,"papers_newest_first":[{"paper":"/paper/developing-visual-augmented-q-a-system-using","title":"Developing Visual Augmented Q&A System using Scalable Vision Embedding Retrieval & Late Interaction Re-ranker","date":"2025-07-16","arxiv_id":"2507.12378","n_code_links":1,"syntology":null},{"paper":null,"title":"Leveraging RAG-LLMs for Urban Mobility Simulation and Analysis","date":"2025-07-14","arxiv_id":"2507.10382","n_code_links":0,"syntology":null},{"paper":"/paper/orchestrator-agent-trust-a-modular-agentic-ai","title":"Orchestrator-Agent Trust: A Modular Agentic AI Visual Classification System with Trust-Aware Orchestration and RAG-Based Reasoning","date":"2025-07-09","arxiv_id":"2507.10571","n_code_links":1,"syntology":null},{"paper":null,"title":"The Dark Side of LLMs Agent-based Attacks for Complete Computer Takeover","date":"2025-07-09","arxiv_id":"2507.06850","n_code_links":0,"syntology":null},{"paper":null,"title":"SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression","date":"2025-07-08","arxiv_id":"2507.05633","n_code_links":0,"syntology":null},{"paper":null,"title":"CyberRAG: An agentic RAG cyber attack classification and reporting tool","date":"2025-07-03","arxiv_id":"2507.02424","n_code_links":0,"syntology":null},{"paper":null,"title":"Knowledge Protocol Engineering: A New Paradigm for AI in Domain-Specific Knowledge Work","date":"2025-07-03","arxiv_id":"2507.02760","n_code_links":0,"syntology":null},{"paper":null,"title":"Knowledge Augmented Finetuning Matters in both RAG and Agent Based Dialog Systems","date":"2025-06-28","arxiv_id":"2506.22852","n_code_links":0,"syntology":null},{"paper":null,"title":"ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation","date":"2025-06-27","arxiv_id":"2506.21931","n_code_links":0,"syntology":null},{"paper":"/paper/erarag-efficient-and-incremental-retrieval","title":"EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora","date":"2025-06-26","arxiv_id":"2506.20963","n_code_links":1,"syntology":null},{"paper":null,"title":"Leveraging LLM-Assisted Query Understanding for Live Retrieval-Augmented Generation","date":"2025-06-26","arxiv_id":"2506.21384","n_code_links":0,"syntology":null},{"paper":"/paper/psylite-technical-report","title":"PsyLite Technical Report","date":"2025-06-26","arxiv_id":"2506.21536","n_code_links":1,"syntology":null},{"paper":"/paper/response-quality-assessment-for-retrieval","title":"Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal Factuality","date":"2025-06-26","arxiv_id":"2506.20978","n_code_links":1,"syntology":{"ran":0,"of":3,"unverified":3,"pointer_only":3}},{"paper":null,"title":"AI Assistants to Enhance and Exploit the PETSc Knowledge Base","date":"2025-06-25","arxiv_id":"2506.20608","n_code_links":0,"syntology":null},{"paper":null,"title":"CCRS: A Zero-Shot LLM-as-a-Judge Framework for Comprehensive RAG Evaluation","date":"2025-06-25","arxiv_id":"2506.20128","n_code_links":0,"syntology":null},{"paper":null,"title":"Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation","date":"2025-06-25","arxiv_id":"2506.20869","n_code_links":0,"syntology":null},{"paper":null,"title":"Knowledge-Aware Diverse Reranking for Cross-Source Question Answering","date":"2025-06-25","arxiv_id":"2506.20476","n_code_links":0,"syntology":null},{"paper":null,"title":"Memento: Note-Taking for Your Future Self","date":"2025-06-25","arxiv_id":"2506.20642","n_code_links":0,"syntology":null},{"paper":null,"title":"Accurate and Energy Efficient: Local Retrieval-Augmented Generation Models Outperform Commercial Large Language Models in Medical Tasks","date":"2025-06-24","arxiv_id":"2506.20009","n_code_links":0,"syntology":null},{"paper":null,"title":"Controlled Retrieval-augmented Context Evaluation for Long-form RAG","date":"2025-06-24","arxiv_id":"2506.20051","n_code_links":0,"syntology":null},{"paper":null,"title":"Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs","date":"2025-06-24","arxiv_id":"2506.19967","n_code_links":0,"syntology":null},{"paper":null,"title":"KunLunBaizeRAG: Reinforcement Learning Driven Inference Performance Leap for Large Language Models","date":"2025-06-24","arxiv_id":"2506.19466","n_code_links":0,"syntology":null},{"paper":null,"title":"T-CPDL: A Temporal Causal Probabilistic Description Logic for Developing Logic-RAG Agent","date":"2025-06-23","arxiv_id":"2506.18559","n_code_links":0,"syntology":null},{"paper":null,"title":"REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing","date":"2025-06-19","arxiv_id":"2506.16444","n_code_links":0,"syntology":null},{"paper":"/paper/cast-enhancing-code-retrieval-augmented","title":"cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree","date":"2025-06-18","arxiv_id":"2506.15655","n_code_links":1,"syntology":null},{"paper":null,"title":"AviationLLM: An LLM-based Knowledge System for Aviation Training","date":"2025-06-17","arxiv_id":"2506.14336","n_code_links":0,"syntology":null},{"paper":"/paper/lightweight-relevance-grader-in-rag","title":"Lightweight Relevance Grader in RAG","date":"2025-06-17","arxiv_id":"2506.14084","n_code_links":1,"syntology":null},{"paper":null,"title":"RAGtifier: Evaluating RAG Generation Approaches of State-of-the-Art RAG Systems for the SIGIR LiveRAG Competition","date":"2025-06-17","arxiv_id":"2506.14412","n_code_links":0,"syntology":null},{"paper":"/paper/arctic-long-sequence-training-scalable-and","title":"Arctic Long Sequence Training: Scalable And Efficient Training For Multi-Million Token Sequences","date":"2025-06-16","arxiv_id":"2506.13996","n_code_links":2,"syntology":null},{"paper":"/paper/ltrr-learning-to-rank-retrievers-for-llms","title":"LTRR: Learning To Rank Retrievers for LLMs","date":"2025-06-16","arxiv_id":"2506.13743","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/rag","name":"RAG","papers":1281},{"task":"/task/retrieval-augmented-generation","name":"Retrieval-augmented Generation","papers":1083},{"task":"/task/retrieval","name":"Retrieval","papers":943},{"task":"/task/question-answering","name":"Question Answering","papers":315},{"task":"/task/language-modelling","name":"Language Modelling","papers":137},{"task":"/task/large-language-model","name":"Large Language Model","papers":123},{"task":"/task/language-modeling","name":"Language Modeling","papers":116},{"task":"/task/hallucination","name":"Hallucination","papers":114},{"task":"/task/information-retrieval","name":"Information Retrieval","papers":104},{"task":"/task/benchmarking","name":"Benchmarking","papers":52},{"task":"/task/knowledge-graphs","name":"Knowledge Graphs","papers":52},{"task":"/task/text-generation","name":"Text Generation","papers":51},{"task":"/task/answer-generation","name":"Answer Generation","papers":39},{"task":"/task/reranking","name":"Reranking","papers":35},{"task":"/task/chunking","name":"Chunking","papers":34},{"task":"/task/response-generation","name":"Response Generation","papers":34},{"task":"/task/open-domain-question-answering","name":"Open-Domain Question Answering","papers":30},{"task":"/task/decision-making","name":"Decision Making","papers":29},{"task":"/task/prompt-engineering","name":"Prompt Engineering","papers":29},{"task":"/task/in-context-learning","name":"In-Context Learning","papers":27}],"tasks_shown":20,"n_tasks":363,"usage_by_year":[{"year":"2020","papers":2},{"year":"2021","papers":5},{"year":"2022","papers":7},{"year":"2023","papers":35},{"year":"2024","papers":682},{"year":"2025","papers":555}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/rag"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}