{"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/dr3-ask-large-language-models-not-to-give-off","title":"Dr3: Ask Large Language Models Not to Give Off-Topic Answers in Open Domain Multi-Hop Question Answering","arxiv_id":"2403.12393","date":"2024-03-19","proceeding":null,"authors":["Yuan Gao","Yiheng Zhu","Yuanbin Cao","Yinzhi Zhou","Zhen Wu","Yujie Chen","Shenglan Wu","Haoyuan Hu","Xinyu Dai"],"abstract":"Open Domain Multi-Hop Question Answering (ODMHQA) plays a crucial role in Natural Language Processing (NLP) by aiming to answer complex questions through multi-step reasoning over retrieved information from external knowledge sources. Recently, Large Language Models (LLMs) have demonstrated remarkable performance in solving ODMHQA owing to their capabilities including planning, reasoning, and utilizing tools. However, LLMs may generate off-topic answers when attempting to solve ODMHQA, namely the generated answers are irrelevant to the original questions. This issue of off-topic answers accounts for approximately one-third of incorrect answers, yet remains underexplored despite its significance. To alleviate this issue, we propose the Discriminate->Re-Compose->Re- Solve->Re-Decompose (Dr3) mechanism. Specifically, the Discriminator leverages the intrinsic capabilities of LLMs to judge whether the generated answers are off-topic. In cases where an off-topic answer is detected, the Corrector performs step-wise revisions along the reversed reasoning chain (Re-Compose->Re-Solve->Re-Decompose) until the final answer becomes on-topic. Experimental results on the HotpotQA and 2WikiMultiHopQA datasets demonstrate that our Dr3 mechanism considerably reduces the occurrence of off-topic answers in ODMHQA by nearly 13%, improving the performance in Exact Match (EM) by nearly 3% compared to the baseline method without the Dr3 mechanism.","url_abs":"https://arxiv.org/abs/2403.12393v1","url_pdf":"https://arxiv.org/pdf/2403.12393v1.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":"dr3-ask-large-language-models-not-to-give-off","repo_url":"https://github.com/gy915/dr3","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"multi-hop-question-answering","task_name":"Multi-hop Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.12393","atlas_url":"https://app.syntology.ai/?focus=2403.12393","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12393"}},"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/gy915/dr3","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"961911bec23c09ff","entry":"clean_str","repo":"gy915/dr3","repo_kind":"official","path":"ReAct+/wikienv_2.py","file_url":"https://github.com/gy915/dr3/blob/HEAD/ReAct%2B/wikienv_2.py","link_basis":"harvester_set","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":"961911bec23c09ff"}},{"code_sha256_prefix":"cddb97f1118f1d85","entry":"colbertv2_get_request_v2","repo":"gy915/dr3","repo_kind":"official","path":"Dr3/colbert_search_engine.py","file_url":"https://github.com/gy915/dr3/blob/HEAD/Dr3/colbert_search_engine.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":"cddb97f1118f1d85"}},{"code_sha256_prefix":"32a5f1733d9a8971","entry":"f1_score","repo":"gy915/dr3","repo_kind":"official","path":"Dr3/metrics.py","file_url":"https://github.com/gy915/dr3/blob/HEAD/Dr3/metrics.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"32a5f1733d9a8971"}},{"code_sha256_prefix":"1dbe229d47cf737d","entry":"get_metrics","repo":"gy915/dr3","repo_kind":"official","path":"Dr3/metrics.py","file_url":"https://github.com/gy915/dr3/blob/HEAD/Dr3/metrics.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":"1dbe229d47cf737d"}},{"code_sha256_prefix":"dae7ab386661a4f4","entry":"normalize_answer","repo":"gy915/dr3","repo_kind":"official","path":"Dr3/metrics.py","file_url":"https://github.com/gy915/dr3/blob/HEAD/Dr3/metrics.py","link_basis":"harvester_set","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":"dae7ab386661a4f4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}