{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:28:23Z","timestamp":1763191703118,"version":"3.45.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227853","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Improving Mathematical Reasoning Capabilities of Small Language Models via Feedback-Driven Distillation"],"prefix":"10.1109","author":[{"given":"Xunyu","family":"Zhu","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}]},{"given":"Jian","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Normal University,School of Artificial Intelligence,Beijing,China"}]},{"given":"Rong","family":"Yin","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}]},{"given":"Can","family":"Ma","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}]},{"given":"Weiping","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Information Engineering,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8003","article-title":"Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes","volume-title":"Findings of the Association for Computational Linguistics: ACL 2023","author":"Hsieh"},{"key":"ref2","first-page":"14 852","article-title":"Large language models are reasoning teachers","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics","volume":"1","author":"Ho"},{"key":"ref3","first-page":"10 421","article-title":"Specializing smaller language models towards multi-step reasoning","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Fu"},{"key":"ref4","first-page":"7059","article-title":"Distilling reasoning capabilities into smaller language models","volume-title":"Findings of the Association for Computational Linguistics: ACL 2023","author":"Shridhar"},{"article-title":"Pad: Program-aided distillation can teach small models reasoning better than chain-of-thought fine-tuning","year":"2023","author":"Zhu","key":"ref5"},{"key":"ref6","first-page":"106594","article-title":"Distilling mathematical reasoning capabilities into small language models","volume-title":"Neural Networks","volume":"179","author":"Zhu","year":"2024"},{"key":"ref7","first-page":"13 484","article-title":"Self-instruct: Aligning language models with self-generated instructions","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics","volume":"1","author":"Wang"},{"article-title":"Metamath: Bootstrap your own mathematical questions for large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yu","key":"ref8"},{"key":"ref9","first-page":"10 230","article-title":"MuggleMath: Assessing the impact of query and response augmentation on math reasoning","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics","volume":"1","author":"Li"},{"article-title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","volume-title":"The Twelfth International Conference on Learning Representations","author":"Xu","key":"ref10"},{"key":"ref11","first-page":"3134","article-title":"Lion: Adversarial distillation of proprietary large language models","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","author":"Jiang"},{"key":"ref12","first-page":"6498","article-title":"LLM2LLM: Boosting LLMs with novel iterative data enhancement","volume-title":"Findings of the Association for Computational Linguistics: ACL 2024","author":"Lee"},{"key":"ref13","article-title":"Training verifiers to solve math word problems","volume-title":"CoRR","volume":"abs\/2110.14168","author":"Cobbe","year":"2021"},{"key":"ref14","first-page":"975","article-title":"A diverse corpus for evaluating and developing English math word problem solvers","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Miao"},{"key":"ref15","first-page":"2080","article-title":"Are NLP models really able to solve simple math word problems?","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Patel"},{"key":"ref16","first-page":"1743","article-title":"Solving general arithmetic word problems","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"Roy"},{"issue":"70","key":"ref17","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume-title":"Journal of Machine Learning Research","volume":"25","author":"Chung","year":"2024"},{"article-title":"Gpt-4 technical report","year":"2024","author":"Achiam","key":"ref18"},{"article-title":"Palm 2 technical report","year":"2023","author":"Anil","key":"ref19"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref20"},{"article-title":"Code llama: Open foundation models for code","year":"2024","author":"Rozi\u00e8re","key":"ref21"},{"article-title":"Platypus: Quick, cheap, and powerful refinement of llms","year":"2024","author":"Lee","key":"ref22"},{"article-title":"Wizardmath: Empowering mathematical reasoning for large language models via reinforced evol-instruct","year":"2023","author":"Luo","key":"ref23"},{"article-title":"ToRA: A tool-integrated reasoning agent for mathematical problem solving","volume-title":"The Twelfth International Conference on Learning Representations","author":"Gou","key":"ref24"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227853.pdf?arnumber=11227853","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:25:32Z","timestamp":1763191532000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227853\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227853","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}