{"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/divide-and-conquer-for-large-language-models","title":"DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMs","arxiv_id":"2401.05190","date":"2024-01-10","proceeding":null,"authors":["Zijie Meng","Yan Zhang","Zhaopeng Feng","Zuozhu Liu"],"abstract":"Large language models (LLMs) have shown impressive performance in reasoning benchmarks with the emergence of Chain-of-Thought (CoT), particularly in multi-choice question (MCQ). However, current works equally resolve questions regardless of the problem-solving difficulty, leading to an excessive focus on simple items while insufficient attention on intricate ones. To address this challenge, we propose a simple yet effective strategy, Divide and Conquer Reasoning (DCR), to enhance the reasoning capability of LLMs for MCQs, as inspired by human beings using heuristics to first categorize tasks and then handle them separately. In particular, we first categorize questions into two subsets based on confidence score ($\\mathcal{CS}$), which is estimated by statistical frequency of generated answers. Subsequently, we propose Filter Choices based Reasoning (FCR) to improve model performance on MCQs with low ($\\mathcal{CS}$). Our experiments demonstrate that the proposed strategy only costs 85% of SOTA, while still achieves average accuracy improvement of 1.56% across nine datasets including arithmetic, commonsense, and logic reasoning tasks. The code is at \\url{https://github.com/AiMijie/Divide-and-Conquer}","url_abs":"https://arxiv.org/abs/2401.05190v2","url_pdf":"https://arxiv.org/pdf/2401.05190v2.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":"divide-and-conquer-for-large-language-models","repo_url":"https://github.com/aimijie/dcr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"divide-and-conquer-for-large-language-models","repo_url":"https://github.com/aimijie/divide-and-conquer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.05190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05190"}},"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/aimijie/dcr","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aimijie/divide-and-conquer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":8,"ran":8,"repositories":2}},"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":0,"samples":[{"code_sha256_prefix":"372e469b050ee739","entry":"createInput","repo":"aimijie/divide-and-conquer","repo_kind":"official","path":"utils.py","file_url":"https://github.com/aimijie/divide-and-conquer/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"372e469b050ee739"}},{"code_sha256_prefix":"8f022f97a0945aeb","entry":"getPath","repo":"aimijie/divide-and-conquer","repo_kind":"official","path":"utils.py","file_url":"https://github.com/aimijie/divide-and-conquer/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f022f97a0945aeb"}},{"code_sha256_prefix":"ed2a1cf1e9a15cb6","entry":"get_ans_sc","repo":"aimijie/divide-and-conquer","repo_kind":"official","path":"compute_all_acc.py","file_url":"https://github.com/aimijie/divide-and-conquer/blob/HEAD/compute_all_acc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed2a1cf1e9a15cb6"}},{"code_sha256_prefix":"abdc8ec1bd2a34c1","entry":"get_len_and_acc_conquered","repo":"aimijie/divide-and-conquer","repo_kind":"official","path":"compute_all_acc.py","file_url":"https://github.com/aimijie/divide-and-conquer/blob/HEAD/compute_all_acc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"abdc8ec1bd2a34c1"}},{"code_sha256_prefix":"ee7b33e026bff293","entry":"get_len_and_acc_fixed","repo":"aimijie/divide-and-conquer","repo_kind":"official","path":"compute_all_acc.py","file_url":"https://github.com/aimijie/divide-and-conquer/blob/HEAD/compute_all_acc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ee7b33e026bff293"}},{"code_sha256_prefix":"89312e410ccb2f33","entry":"get_sim_an","repo":"aimijie/dcr","repo_kind":"official","path":"split_data.py","file_url":"https://github.com/aimijie/dcr/blob/HEAD/split_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89312e410ccb2f33"}},{"code_sha256_prefix":"2b3be75199e4658e","entry":"judge_confidence","repo":"aimijie/dcr","repo_kind":"official","path":"split_data.py","file_url":"https://github.com/aimijie/dcr/blob/HEAD/split_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b3be75199e4658e"}},{"code_sha256_prefix":"42008063fbb6e058","entry":"setPrompt","repo":"aimijie/divide-and-conquer","repo_kind":"official","path":"utils.py","file_url":"https://github.com/aimijie/divide-and-conquer/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42008063fbb6e058"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}