{"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/textit-skintern-internalizing-symbolic","title":"$\\textit{SKIntern}$: Internalizing Symbolic Knowledge for Distilling Better CoT Capabilities into Small Language Models","arxiv_id":"2409.13183","date":"2024-09-20","proceeding":null,"authors":["Huanxuan Liao","Shizhu He","Yupu Hao","Xiang Li","Yuanzhe Zhang","Jun Zhao","Kang Liu"],"abstract":"Small Language Models (SLMs) are attracting attention due to the high computational demands and privacy concerns of Large Language Models (LLMs). Some studies fine-tune SLMs using Chains of Thought (CoT) data distilled from LLMs, aiming to enhance their reasoning ability. Furthermore, Some CoT distillation methods introduce external symbolic knowledge into the generation process to improve the limited knowledge memory, reasoning ability and out-of-domain (OOD) generalization of SLMs. However, the introduction of symbolic knowledge increases computational overhead and introduces potential noise. In this paper, we introduce $\\textit{SKIntern}$, an innovative approach that empowers SLMs to internalize symbolic knowledge and few-shot examples gradually through a progressive fine-tuning process, guided by a predefined linear decay schedule under curriculum learning. By efficiently internalizing knowledge, $\\textit{SKIntern}$ reduces computational overhead and speeds up the reasoning process by focusing solely on the question during inference. It outperforms state-of-the-art baselines by over 5\\%, while reducing inference costs (measured in FLOPs) by up to $4\\times$ across a wide range of SLMs in both in-domain (ID) and out-of-domain (OOD) tasks. Our code will be available at \\url{https://github.com/Xnhyacinth/SKIntern}.","url_abs":"https://arxiv.org/abs/2409.13183v2","url_pdf":"https://arxiv.org/pdf/2409.13183v2.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":"textit-skintern-internalizing-symbolic","repo_url":"https://github.com/xnhyacinth/skintern","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.13183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13183"}},"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/xnhyacinth/skintern","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"a46f2292d2a56f74","entry":"eval_csqa","repo":"xnhyacinth/skintern","repo_kind":"official","path":"src/llamafactory/eval/eval_bbh.py","file_url":"https://github.com/xnhyacinth/skintern/blob/HEAD/src/llamafactory/eval/eval_bbh.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a46f2292d2a56f74"}},{"code_sha256_prefix":"96d50158e2109ae3","entry":"eval_triviaqa","repo":"xnhyacinth/skintern","repo_kind":"official","path":"src/llamafactory/eval/eval_triviaqa.py","file_url":"https://github.com/xnhyacinth/skintern/blob/HEAD/src/llamafactory/eval/eval_triviaqa.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"96d50158e2109ae3"}},{"code_sha256_prefix":"57583cf880d95444","entry":"jsonify","repo":"xnhyacinth/skintern","repo_kind":"official","path":"src/llamafactory/api/common.py","file_url":"https://github.com/xnhyacinth/skintern/blob/HEAD/src/llamafactory/api/common.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"57583cf880d95444"}},{"code_sha256_prefix":"3f5cda900eb73d2b","entry":"create_score_evaluation_response","repo":"xnhyacinth/skintern","repo_kind":"official","path":"src/llamafactory/api/chat.py","file_url":"https://github.com/xnhyacinth/skintern/blob/HEAD/src/llamafactory/api/chat.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3f5cda900eb73d2b"}},{"code_sha256_prefix":"87aa9acaa81294f5","entry":"dictify","repo":"xnhyacinth/skintern","repo_kind":"official","path":"src/llamafactory/api/common.py","file_url":"https://github.com/xnhyacinth/skintern/blob/HEAD/src/llamafactory/api/common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"87aa9acaa81294f5"}},{"code_sha256_prefix":"3fe26ff9ae58c1cf","entry":"eval_csqa_chat","repo":"xnhyacinth/skintern","repo_kind":"official","path":"src/llamafactory/eval/eval_bbh.py","file_url":"https://github.com/xnhyacinth/skintern/blob/HEAD/src/llamafactory/eval/eval_bbh.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3fe26ff9ae58c1cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}