{"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/democratizing-reasoning-ability-tailored","title":"Democratizing Reasoning Ability: Tailored Learning from Large Language Model","arxiv_id":"2310.13332","date":"2023-10-20","proceeding":null,"authors":["Zhaoyang Wang","Shaohan Huang","Yuxuan Liu","Jiahai Wang","Minghui Song","Zihan Zhang","Haizhen Huang","Furu Wei","Weiwei Deng","Feng Sun","Qi Zhang"],"abstract":"Large language models (LLMs) exhibit impressive emergent abilities in natural language processing, but their democratization is hindered due to huge computation requirements and closed-source nature. Recent research on advancing open-source smaller LMs by distilling knowledge from black-box LLMs has obtained promising results in the instruction-following ability. However, the reasoning ability which is more challenging to foster, is relatively rarely explored. In this paper, we propose a tailored learning approach to distill such reasoning ability to smaller LMs to facilitate the democratization of the exclusive reasoning ability. In contrast to merely employing LLM as a data annotator, we exploit the potential of LLM as a reasoning teacher by building an interactive multi-round learning paradigm. This paradigm enables the student to expose its deficiencies to the black-box teacher who then can provide customized training data in return. Further, to exploit the reasoning potential of the smaller LM, we propose self-reflection learning to motivate the student to learn from self-made mistakes. The learning from self-reflection and LLM are all tailored to the student's learning status, thanks to the seamless integration with the multi-round learning paradigm. Comprehensive experiments and analysis on mathematical and commonsense reasoning tasks demonstrate the effectiveness of our method. The code will be available at https://github.com/Raibows/Learn-to-Reason.","url_abs":"https://arxiv.org/abs/2310.13332v1","url_pdf":"https://arxiv.org/pdf/2310.13332v1.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":"democratizing-reasoning-ability-tailored","repo_url":"https://github.com/raibows/learn-to-reason","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2310.13332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13332"}},"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/raibows/learn-to-reason","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Raibows/Learn-to-Reason","reach":{"status":"ok"}}],"summary":{"ran":5,"unverified":3},"by_repo_kind":{"official":{"samples":8,"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":8,"samples":[{"code_sha256_prefix":"ab1a4030ec230388","entry":"add_eos_token","repo":"Raibows/Learn-to-Reason","repo_kind":"official","path":"preprocessors.py","file_url":"https://github.com/Raibows/Learn-to-Reason/blob/HEAD/preprocessors.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":"ab1a4030ec230388"}},{"code_sha256_prefix":"4b72086bac0f516f","entry":"get_generation_config","repo":"Raibows/Learn-to-Reason","repo_kind":"official","path":"utils.py","file_url":"https://github.com/Raibows/Learn-to-Reason/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4b72086bac0f516f"}},{"code_sha256_prefix":"3d3a5e750bd34baf","entry":"metahelp","repo":"Raibows/Learn-to-Reason","repo_kind":"official","path":"args.py","file_url":"https://github.com/Raibows/Learn-to-Reason/blob/HEAD/args.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":"3d3a5e750bd34baf"}},{"code_sha256_prefix":"f8d30c749c7c5042","entry":"prepare_model","repo":"Raibows/Learn-to-Reason","repo_kind":"official","path":"utils.py","file_url":"https://github.com/Raibows/Learn-to-Reason/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f8d30c749c7c5042"}},{"code_sha256_prefix":"46a48a87dbf801a9","entry":"tools_is_decoder_only","repo":"Raibows/Learn-to-Reason","repo_kind":"official","path":"tools.py","file_url":"https://github.com/Raibows/Learn-to-Reason/blob/HEAD/tools.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":"46a48a87dbf801a9"}},{"code_sha256_prefix":"838de4f52529652c","entry":"prepare_prompt","repo":"Raibows/Learn-to-Reason","repo_kind":"official","path":"preprocessors.py","file_url":"https://github.com/Raibows/Learn-to-Reason/blob/HEAD/preprocessors.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":"838de4f52529652c"}},{"code_sha256_prefix":"362d60e4e55dc5db","entry":"prepend_hint","repo":"Raibows/Learn-to-Reason","repo_kind":"official","path":"preprocessors.py","file_url":"https://github.com/Raibows/Learn-to-Reason/blob/HEAD/preprocessors.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":"362d60e4e55dc5db"}},{"code_sha256_prefix":"0b83f5642399d18d","entry":"tools_prepare_trainargs_note","repo":"Raibows/Learn-to-Reason","repo_kind":"official","path":"tools.py","file_url":"https://github.com/Raibows/Learn-to-Reason/blob/HEAD/tools.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":"0b83f5642399d18d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}