{"work":{"id":"b80d2790-6cd9-4c87-b3c4-de404f99a80e","openalex_id":"https://openalex.org/W2077677227","doi":"10.1186/1476-072x-8-72","arxiv_id":"2312.10997","raw_key":null,"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","authors":null,"authors_text":"Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Qianyu Guo, Meng Wang, and Haofen Wang","year":2023,"venue":"cs.CL","abstract":"Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by incorporating knowledge from external databases. This enhances the accuracy and credibility of the generation, particularly for knowledge-intensive tasks, and allows for continuous knowledge updates and integration of domain-specific information. RAG synergistically merges LLMs' intrinsic knowledge with the vast, dynamic repositories of external databases. This comprehensive review paper offers a detailed examination of the progression of RAG paradigms, encompassing the Naive RAG, the Advanced RAG, and the Modular RAG. It meticulously scrutinizes the tripartite foundation of RAG frameworks, which includes the retrieval, the generation and the augmentation techniques. The paper highlights the state-of-the-art technologies embedded in each of these critical components, providing a profound understanding of the advancements in RAG systems. Furthermore, this paper introduces up-to-date evaluation framework and benchmark. At the end, this article delineates the challenges currently faced and points out prospective avenues for research and development.","external_url":"https://arxiv.org/abs/2312.10997","cited_by_count":17,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2312.10997","created_at":"2026-05-08T20:09:07.212069+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","render_title":"Retrieval-Augmented Generation for Large Language Models: A Survey"},"hub":{"state":{"work_id":"b80d2790-6cd9-4c87-b3c4-de404f99a80e","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":402,"external_cited_by_count":17,"distinct_field_count":32,"first_pith_cited_at":"2024-01-21T23:36:14+00:00","last_pith_cited_at":"2026-07-09T14:33:47+00:00","author_build_status":"needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T19:49:25.793890+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":63},{"context_role":"method","n":5},{"context_role":"dataset","n":2}],"polarity_counts":[{"context_polarity":"background","n":60},{"context_polarity":"use_method","n":5},{"context_polarity":"unclear","n":2},{"context_polarity":"use_dataset","n":2},{"context_polarity":"support","n":1}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","claims":[{"claim_text":"Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by incorporating knowledge from external databases. This enhances the accuracy and credibility of the generation, particularly for knowledge-intensive tasks, and allows for continuous knowledge updates and integration of domain-specific information. RAG synergistically merges LLMs' intrinsic knowledge with the vast, dynamic repositories of exte","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Retrieval-Augmented Generation for Large Language Models: A Survey because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T23:23:54.266393+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"b816b596-4a63-43fd-9294-ff550f233b50","orcid":null,"display_name":"Yunfan Gao"},{"id":"6dea5b23-7afe-4266-b11b-fd81cb4a8930","orcid":null,"display_name":"Yun Xiong"},{"id":"bf8c33f7-363a-4643-8cd2-60a48564aac0","orcid":null,"display_name":"Xinyu Gao"},{"id":"0e0ccddd-13e0-47f7-bcd2-3077da3d7f82","orcid":null,"display_name":"Kangxiang Jia"},{"id":"f03629fe-3e76-4e12-8b96-432318f4e613","orcid":null,"display_name":"Jinliu Pan"},{"id":"c5a54a94-9a83-4227-8231-b2334b989e09","orcid":null,"display_name":"Yuxi Bi"}]},"error":null,"updated_at":"2026-05-13T23:23:54.259434+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-13T23:23:58.036479+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","work_id":"588618d7-fd41-4053-b34d-a981f8793039","shared_citers":28},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":23},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":21},{"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","shared_citers":16},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":14},{"title":"DeepSeek-V3 Technical Report","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","shared_citers":13},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":12},{"title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","work_id":"27eaec54-c105-4969-8188-da5f0fca3688","shared_citers":12},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":12},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":11},{"title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","work_id":"6118de04-b8eb-4163-826a-0f91a1bcdf14","shared_citers":11},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":11},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":10},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":10},{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":9},{"title":"GPT-4o System Card","work_id":"f37bf1c7-4964-4e56-9762-d20da8d9009f","shared_citers":9},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":9},{"title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","work_id":"a5aed26c-a248-48b6-a59e-f7693fcb180a","shared_citers":9},{"title":"Retrieval-augmented generation for ai-generated content: A survey","work_id":"5440e856-5c59-44cb-8ea8-f1c3591c7425","shared_citers":9},{"title":"A-MEM: Agentic Memory for LLM Agents","work_id":"3b98feb2-fdb1-479a-bbe4-2c298a4592e2","shared_citers":8},{"title":"LoRA: Low-Rank Adaptation of Large Language Models","work_id":"0426219a-789e-4964-adc8-a04538510818","shared_citers":8},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":8},{"title":"Mistral 7B","work_id":"eb5e1305-ad11-4875-ad8d-ad8b8f697599","shared_citers":8},{"title":"OpenAI GPT-5 System Card","work_id":"ca87689a-0d29-4476-b504-b65dbbb08af4","shared_citers":8}],"time_series":[{"n":6,"year":2024},{"n":1,"year":2025},{"n":135,"year":2026}]},"error":null,"updated_at":"2026-05-13T23:23:53.008473+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"fixed":1,"items":[{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-13T23:24:10.854035+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","claims":[{"claim_text":"Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by incorporating knowledge from external databases. This enhances the accuracy and credibility of the generation, particularly for knowledge-intensive tasks, and allows for continuous knowledge updates and integration of domain-specific information. RAG synergistically merges LLMs' intrinsic knowledge with the vast, dynamic repositories of exte","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Retrieval-Augmented Generation for Large Language Models: A Survey because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T23:24:06.380669+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","claims":[{"claim_text":"Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by incorporating knowledge from external databases. This enhances the accuracy and credibility of the generation, particularly for knowledge-intensive tasks, and allows for continuous knowledge updates and integration of domain-specific information. RAG synergistically merges LLMs' intrinsic knowledge with the vast, dynamic repositories of exte","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Retrieval-Augmented Generation for Large Language Models: A Survey because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-13T23:23:54.263542+00:00"}},"summary":{"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","claims":[{"claim_text":"Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by incorporating knowledge from external databases. This enhances the accuracy and credibility of the generation, particularly for knowledge-intensive tasks, and allows for continuous knowledge updates and integration of domain-specific information. RAG synergistically merges LLMs' intrinsic knowledge with the vast, dynamic repositories of exte","claim_type":"abstract","evidence_strength":"source_metadata"}],"why_cited":"Pith tracks Retrieval-Augmented Generation for Large Language Models: A Survey because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","work_id":"588618d7-fd41-4053-b34d-a981f8793039","shared_citers":28},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":23},{"title":"Qwen3 Technical Report","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","shared_citers":21},{"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","shared_citers":16},{"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","shared_citers":14},{"title":"DeepSeek-V3 Technical Report","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","shared_citers":13},{"title":"MemGPT: Towards LLMs as Operating Systems","work_id":"2698f5ad-c84c-40ca-b839-0912dae10ba2","shared_citers":12},{"title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","work_id":"27eaec54-c105-4969-8188-da5f0fca3688","shared_citers":12},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":12},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":11},{"title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","work_id":"6118de04-b8eb-4163-826a-0f91a1bcdf14","shared_citers":11},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":11},{"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","shared_citers":10},{"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","shared_citers":10},{"title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","shared_citers":9},{"title":"GPT-4o System Card","work_id":"f37bf1c7-4964-4e56-9762-d20da8d9009f","shared_citers":9},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":9},{"title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","work_id":"a5aed26c-a248-48b6-a59e-f7693fcb180a","shared_citers":9},{"title":"Retrieval-augmented generation for ai-generated content: A survey","work_id":"5440e856-5c59-44cb-8ea8-f1c3591c7425","shared_citers":9},{"title":"A-MEM: Agentic Memory for LLM Agents","work_id":"3b98feb2-fdb1-479a-bbe4-2c298a4592e2","shared_citers":8},{"title":"LoRA: Low-Rank Adaptation of Large Language Models","work_id":"0426219a-789e-4964-adc8-a04538510818","shared_citers":8},{"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","shared_citers":8},{"title":"Mistral 7B","work_id":"eb5e1305-ad11-4875-ad8d-ad8b8f697599","shared_citers":8},{"title":"OpenAI GPT-5 System Card","work_id":"ca87689a-0d29-4476-b504-b65dbbb08af4","shared_citers":8}],"time_series":[{"n":6,"year":2024},{"n":1,"year":2025},{"n":135,"year":2026}]},"authors":[{"id":"f03629fe-3e76-4e12-8b96-432318f4e613","orcid":null,"display_name":"Jinliu Pan","source":"manual","import_confidence":0.72},{"id":"0e0ccddd-13e0-47f7-bcd2-3077da3d7f82","orcid":null,"display_name":"Kangxiang Jia","source":"manual","import_confidence":0.72},{"id":"bf8c33f7-363a-4643-8cd2-60a48564aac0","orcid":null,"display_name":"Xinyu Gao","source":"manual","import_confidence":0.72},{"id":"b816b596-4a63-43fd-9294-ff550f233b50","orcid":null,"display_name":"Yunfan Gao","source":"manual","import_confidence":0.72},{"id":"6dea5b23-7afe-4266-b11b-fd81cb4a8930","orcid":null,"display_name":"Yun Xiong","source":"manual","import_confidence":0.72},{"id":"c5a54a94-9a83-4227-8231-b2334b989e09","orcid":null,"display_name":"Yuxi Bi","source":"manual","import_confidence":0.72}]}}