{"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/mcc-kd-multi-cot-consistent-knowledge","title":"MCC-KD: Multi-CoT Consistent Knowledge Distillation","arxiv_id":"2310.14747","date":"2023-10-23","proceeding":null,"authors":["Hongzhan Chen","Siyue Wu","Xiaojun Quan","Rui Wang","Ming Yan","Ji Zhang"],"abstract":"Large language models (LLMs) have showcased remarkable capabilities in complex reasoning through chain of thought (CoT) prompting. Recently, there has been a growing interest in transferring these reasoning abilities from LLMs to smaller models. However, achieving both the diversity and consistency in rationales presents a challenge. In this paper, we focus on enhancing these two aspects and propose Multi-CoT Consistent Knowledge Distillation (MCC-KD) to efficiently distill the reasoning capabilities. In MCC-KD, we generate multiple rationales for each question and enforce consistency among the corresponding predictions by minimizing the bidirectional KL-divergence between the answer distributions. We investigate the effectiveness of MCC-KD with different model architectures (LLaMA/FlanT5) and various model scales (3B/7B/11B/13B) on both mathematical reasoning and commonsense reasoning benchmarks. The empirical results not only confirm MCC-KD's superior performance on in-distribution datasets but also highlight its robust generalization ability on out-of-distribution datasets.","url_abs":"https://arxiv.org/abs/2310.14747v3","url_pdf":"https://arxiv.org/pdf/2310.14747v3.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":"mcc-kd-multi-cot-consistent-knowledge","repo_url":"https://github.com/homzer/MCC-KD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"}],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.14747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14747"}},"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/homzer/MCC-KD","reach":{"status":"ok"}}],"summary":{"ran":5,"unverified":2},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"24ed0ef7f8b7dd50","entry":"get_layer_id","repo":"homzer/MCC-KD","repo_kind":"official","path":"src/checkpoint.py","file_url":"https://github.com/homzer/MCC-KD/blob/HEAD/src/checkpoint.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":"24ed0ef7f8b7dd50"}},{"code_sha256_prefix":"2541a463c617915f","entry":"is_col_parallel","repo":"homzer/MCC-KD","repo_kind":"official","path":"src/checkpoint.py","file_url":"https://github.com/homzer/MCC-KD/blob/HEAD/src/checkpoint.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":"2541a463c617915f"}},{"code_sha256_prefix":"8ae8c583b21633b3","entry":"is_digit","repo":"homzer/MCC-KD","repo_kind":"official","path":"src/math.py","file_url":"https://github.com/homzer/MCC-KD/blob/HEAD/src/math.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":"8ae8c583b21633b3"}},{"code_sha256_prefix":"1326a47fdc9814bd","entry":"is_parallel","repo":"homzer/MCC-KD","repo_kind":"official","path":"src/checkpoint.py","file_url":"https://github.com/homzer/MCC-KD/blob/HEAD/src/checkpoint.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":"1326a47fdc9814bd"}},{"code_sha256_prefix":"68b923890cd0fcc5","entry":"n_round","repo":"homzer/MCC-KD","repo_kind":"official","path":"src/canvas.py","file_url":"https://github.com/homzer/MCC-KD/blob/HEAD/src/canvas.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":"68b923890cd0fcc5"}},{"code_sha256_prefix":"f4f7ce0a9663a482","entry":"call_with_timeout","repo":"homzer/MCC-KD","repo_kind":"official","path":"src/math.py","file_url":"https://github.com/homzer/MCC-KD/blob/HEAD/src/math.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":"f4f7ce0a9663a482"}},{"code_sha256_prefix":"2a595d76f2117c3e","entry":"symbolic_equal","repo":"homzer/MCC-KD","repo_kind":"official","path":"src/math.py","file_url":"https://github.com/homzer/MCC-KD/blob/HEAD/src/math.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":"2a595d76f2117c3e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}