{"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/longrag-a-dual-perspective-retrieval","title":"LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering","arxiv_id":"2410.18050","date":"2024-10-23","proceeding":null,"authors":["Qingfei Zhao","Ruobing Wang","Yukuo Cen","Daren Zha","Shicheng Tan","Yuxiao Dong","Jie Tang"],"abstract":"Long-Context Question Answering (LCQA), a challenging task, aims to reason over long-context documents to yield accurate answers to questions. Existing long-context Large Language Models (LLMs) for LCQA often struggle with the \"lost in the middle\" issue. Retrieval-Augmented Generation (RAG) mitigates this issue by providing external factual evidence. However, its chunking strategy disrupts the global long-context information, and its low-quality retrieval in long contexts hinders LLMs from identifying effective factual details due to substantial noise. To this end, we propose LongRAG, a general, dual-perspective, and robust LLM-based RAG system paradigm for LCQA to enhance RAG's understanding of complex long-context knowledge (i.e., global information and factual details). We design LongRAG as a plug-and-play paradigm, facilitating adaptation to various domains and LLMs. Extensive experiments on three multi-hop datasets demonstrate that LongRAG significantly outperforms long-context LLMs (up by 6.94%), advanced RAG (up by 6.16%), and Vanilla RAG (up by 17.25%). Furthermore, we conduct quantitative ablation studies and multi-dimensional analyses, highlighting the effectiveness of the system's components and fine-tuning strategies. Data and code are available at https://github.com/QingFei1/LongRAG.","url_abs":"https://arxiv.org/abs/2410.18050v2","url_pdf":"https://arxiv.org/pdf/2410.18050v2.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":"longrag-a-dual-perspective-retrieval","repo_url":"https://github.com/qingfei1/longrag","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"chunking","task_name":"Chunking"},{"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":"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=2410.18050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18050"}},"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/qingfei1/longrag","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/QingFei1/LongRAG","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":8,"ran":2,"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":8,"samples":[{"code_sha256_prefix":"d8e7ceb7ac0087e6","entry":"f1_score","repo":"QingFei1/LongRAG","repo_kind":"official","path":"src/metric.py","file_url":"https://github.com/QingFei1/LongRAG/blob/HEAD/src/metric.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d8e7ceb7ac0087e6"}},{"code_sha256_prefix":"c6a80c065d2e4851","entry":"normalize_answer","repo":"QingFei1/LongRAG","repo_kind":"official","path":"src/metric.py","file_url":"https://github.com/QingFei1/LongRAG/blob/HEAD/src/metric.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c6a80c065d2e4851"}},{"code_sha256_prefix":"bc5805ac2847e605","entry":"get_word_count","repo":"QingFei1/LongRAG","repo_kind":"official","path":"src/gen_index.py","file_url":"https://github.com/QingFei1/LongRAG/blob/HEAD/src/gen_index.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":"bc5805ac2847e605"}},{"code_sha256_prefix":"66aecc670573f9dd","entry":"predata","repo":"QingFei1/LongRAG","repo_kind":"official","path":"src/gen_LRGinstruction.py","file_url":"https://github.com/QingFei1/LongRAG/blob/HEAD/src/gen_LRGinstruction.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":"66aecc670573f9dd"}},{"code_sha256_prefix":"6811a69d3f3d6ccb","entry":"process_data","repo":"QingFei1/LongRAG","repo_kind":"official","path":"src/gen_index.py","file_url":"https://github.com/QingFei1/LongRAG/blob/HEAD/src/gen_index.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":"6811a69d3f3d6ccb"}},{"code_sha256_prefix":"943b50b1dc1bfec5","entry":"qa_f1_score","repo":"QingFei1/LongRAG","repo_kind":"official","path":"src/metric.py","file_url":"https://github.com/QingFei1/LongRAG/blob/HEAD/src/metric.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":"943b50b1dc1bfec5"}},{"code_sha256_prefix":"97057ce82fe153ae","entry":"remove_consecutive_repeated_sentences","repo":"QingFei1/LongRAG","repo_kind":"official","path":"src/api.py","file_url":"https://github.com/QingFei1/LongRAG/blob/HEAD/src/api.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":"97057ce82fe153ae"}},{"code_sha256_prefix":"00adbf7ca43ffd6f","entry":"split_sentences","repo":"QingFei1/LongRAG","repo_kind":"official","path":"src/gen_index.py","file_url":"https://github.com/QingFei1/LongRAG/blob/HEAD/src/gen_index.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":"00adbf7ca43ffd6f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}