{"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/merging-generated-and-retrieved-knowledge-for","title":"Merging Generated and Retrieved Knowledge for Open-Domain QA","arxiv_id":"2310.14393","date":"2023-10-22","proceeding":null,"authors":["Yunxiang Zhang","Muhammad Khalifa","Lajanugen Logeswaran","Moontae Lee","Honglak Lee","Lu Wang"],"abstract":"Open-domain question answering (QA) systems are often built with retrieval modules. However, retrieving passages from a given source is known to suffer from insufficient knowledge coverage. Alternatively, prompting large language models (LLMs) to generate contextual passages based on their parametric knowledge has been shown to improve QA performance. Yet, LLMs tend to \"hallucinate\" content that conflicts with the retrieved knowledge. Based on the intuition that answers supported by both sources are more likely to be correct, we propose COMBO, a Compatibility-Oriented knowledge Merging for Better Open-domain QA framework, to effectively leverage the two sources of information. Concretely, we match LLM-generated passages with retrieved counterparts into compatible pairs, based on discriminators trained with silver compatibility labels. Then a Fusion-in-Decoder-based reader model handles passage pairs to arrive at the final answer. Experiments show that COMBO outperforms competitive baselines on three out of four tested open-domain QA benchmarks. Further analysis reveals that our proposed framework demonstrates greater efficacy in scenarios with a higher degree of knowledge conflicts.","url_abs":"https://arxiv.org/abs/2310.14393v1","url_pdf":"https://arxiv.org/pdf/2310.14393v1.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":"merging-generated-and-retrieved-knowledge-for","repo_url":"https://github.com/yunx-z/combo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.14393","atlas_url":"https://app.syntology.ai/?focus=2310.14393","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14393"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/yunx-z/combo","reach":{"status":"ok"}}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":6,"samples":[{"code_sha256_prefix":"3c9429bad228b98b","entry":"check_answer","repo":"yunx-z/combo","repo_kind":"official","path":"passage_matching/evaluation.py","file_url":"https://github.com/yunx-z/combo/blob/HEAD/passage_matching/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3c9429bad228b98b"}},{"code_sha256_prefix":"2075373a61e75fd7","entry":"has_answer","repo":"yunx-z/combo","repo_kind":"official","path":"passage_matching/evaluation.py","file_url":"https://github.com/yunx-z/combo/blob/HEAD/passage_matching/evaluation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2075373a61e75fd7"}},{"code_sha256_prefix":"4cca112e5e6da5dc","entry":"normalize_answer","repo":"yunx-z/combo","repo_kind":"official","path":"passage_matching/evaluation.py","file_url":"https://github.com/yunx-z/combo/blob/HEAD/passage_matching/evaluation.py","link_basis":"harvester_set","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":"4cca112e5e6da5dc"}},{"code_sha256_prefix":"47fc27396a07c2f4","entry":"resize_list","repo":"yunx-z/combo","repo_kind":"official","path":"passage_matching/build_psg_pairs.py","file_url":"https://github.com/yunx-z/combo/blob/HEAD/passage_matching/build_psg_pairs.py","link_basis":"first_harvest_node","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":"47fc27396a07c2f4"}},{"code_sha256_prefix":"6428ebca756f3ea1","entry":"resize_matrix","repo":"yunx-z/combo","repo_kind":"official","path":"passage_matching/build_psg_pairs.py","file_url":"https://github.com/yunx-z/combo/blob/HEAD/passage_matching/build_psg_pairs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6428ebca756f3ea1"}},{"code_sha256_prefix":"83360c6f5e584874","entry":"get_nli_score","repo":"yunx-z/combo","repo_kind":"official","path":"passage_matching/build_psg_pairs.py","file_url":"https://github.com/yunx-z/combo/blob/HEAD/passage_matching/build_psg_pairs.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":"83360c6f5e584874"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}