{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/rationale-guided-retrieval-augmented","title":"Rationale-Guided Retrieval Augmented Generation for Medical Question Answering","arxiv_id":"2411.00300","date":"2024-11-01","proceeding":null,"authors":["Jiwoong Sohn","Yein Park","Chanwoong Yoon","Sihyeon Park","Hyeon Hwang","Mujeen Sung","Hyunjae Kim","Jaewoo Kang"],"abstract":"Large language models (LLM) hold significant potential for applications in biomedicine, but they struggle with hallucinations and outdated knowledge. While retrieval-augmented generation (RAG) is generally employed to address these issues, it also has its own set of challenges: (1) LLMs are vulnerable to irrelevant or incorrect context, (2) medical queries are often not well-targeted for helpful information, and (3) retrievers are prone to bias toward the specific source corpus they were trained on. In this study, we present RAG$^2$ (RAtionale-Guided RAG), a new framework for enhancing the reliability of RAG in biomedical contexts. RAG$^2$ incorporates three key innovations: a small filtering model trained on perplexity-based labels of rationales, which selectively augments informative snippets of documents while filtering out distractors; LLM-generated rationales as queries to improve the utility of retrieved snippets; a structure designed to retrieve snippets evenly from a comprehensive set of four biomedical corpora, effectively mitigating retriever bias. Our experiments demonstrate that RAG$^2$ improves the state-of-the-art LLMs of varying sizes, with improvements of up to 6.1\\%, and it outperforms the previous best medical RAG model by up to 5.6\\% across three medical question-answering benchmarks. Our code is available at https://github.com/dmis-lab/RAG2.","url_abs":"https://arxiv.org/abs/2411.00300v1","url_pdf":"https://arxiv.org/pdf/2411.00300v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"rationale-guided-retrieval-augmented","repo_url":"https://github.com/dmis-lab/rag2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"Medical Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"rag","task_name":"RAG"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"rag","method_name":"RAG"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"set","method_name":"SET"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.00300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00300"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dmis-lab/rag2","reach":{"status":"ok"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":9,"samples":[{"code_sha256_prefix":"20436091ccb0536c","entry":"combine_query_evidence","repo":"dmis-lab/rag2","repo_kind":"official","path":"retriever/rerank.py","file_url":"https://github.com/dmis-lab/rag2/blob/HEAD/retriever/rerank.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"20436091ccb0536c"}},{"code_sha256_prefix":"dcb61d0b5ef6fc35","entry":"cpg_index_create","repo":"dmis-lab/rag2","repo_kind":"official","path":"retriever/retrieve.py","file_url":"https://github.com/dmis-lab/rag2/blob/HEAD/retriever/retrieve.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dcb61d0b5ef6fc35"}},{"code_sha256_prefix":"f013b9029a24e889","entry":"load_model","repo":"dmis-lab/rag2","repo_kind":"official","path":"classifier/utils.py","file_url":"https://github.com/dmis-lab/rag2/blob/HEAD/classifier/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f013b9029a24e889"}},{"code_sha256_prefix":"87333551aaf59069","entry":"pmc_index_create","repo":"dmis-lab/rag2","repo_kind":"official","path":"retriever/retrieve.py","file_url":"https://github.com/dmis-lab/rag2/blob/HEAD/retriever/retrieve.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"87333551aaf59069"}},{"code_sha256_prefix":"662378e999a32811","entry":"preprocess_dataset","repo":"dmis-lab/rag2","repo_kind":"official","path":"classifier/utils.py","file_url":"https://github.com/dmis-lab/rag2/blob/HEAD/classifier/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"662378e999a32811"}},{"code_sha256_prefix":"dcfd3106a6eeb7be","entry":"preprocess_features_function","repo":"dmis-lab/rag2","repo_kind":"official","path":"classifier/utils.py","file_url":"https://github.com/dmis-lab/rag2/blob/HEAD/classifier/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dcfd3106a6eeb7be"}},{"code_sha256_prefix":"e55528aca1da09c1","entry":"pubmed_index_create","repo":"dmis-lab/rag2","repo_kind":"official","path":"retriever/retrieve.py","file_url":"https://github.com/dmis-lab/rag2/blob/HEAD/retriever/retrieve.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e55528aca1da09c1"}},{"code_sha256_prefix":"0527070a6ee7eb7e","entry":"query_encode","repo":"dmis-lab/rag2","repo_kind":"official","path":"retriever/query_encode.py","file_url":"https://github.com/dmis-lab/rag2/blob/HEAD/retriever/query_encode.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0527070a6ee7eb7e"}},{"code_sha256_prefix":"f60fd4c647296b03","entry":"rerank","repo":"dmis-lab/rag2","repo_kind":"official","path":"retriever/rerank.py","file_url":"https://github.com/dmis-lab/rag2/blob/HEAD/retriever/rerank.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f60fd4c647296b03"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}