{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T15:04:49Z","timestamp":1789311889600,"version":"build-2803163510"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100005645","name":"Socialist Republic of Vietnam Ministry of Education and Training","doi-asserted-by":"publisher","award":["B2026\\u2013BKA\\u201301"],"award-info":[{"award-number":["B2026\\u2013BKA\\u201301"]}],"id":[{"id":"10.13039\/501100005645","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.knosys.2026.116606","type":"journal-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T14:58:30Z","timestamp":1783781910000},"page":"116606","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Discord: Enhancing knowledge distillation via cross-chain of thought and optimal transport alignment between models with different tokenizers"],"prefix":"10.1016","volume":"351","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8895-6051","authenticated-orcid":false,"given":"Nam Le","family":"Hai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anh Duc","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7193-9793","authenticated-orcid":false,"given":"Tu","family":"Vu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0011-5137","authenticated-orcid":false,"given":"Linh Ngo","family":"Van","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116606_b1","series-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"10.1016\/j.knosys.2026.116606_b2","series-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.knosys.2026.116606_b3","series-title":"Mistral 7B","author":"Jiang","year":"2023"},{"key":"10.1016\/j.knosys.2026.116606_b4","series-title":"Mixtral of experts","author":"Jiang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116606_b5","series-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","author":"Guo","year":"2025"},{"key":"10.1016\/j.knosys.2026.116606_b6","series-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"10.1016\/j.knosys.2026.116606_b7","series-title":"Do not blindly imitate the teacher: Using perturbed loss for knowledge distillation","author":"Zhang","year":"2023"},{"key":"10.1016\/j.knosys.2026.116606_b8","doi-asserted-by":"crossref","unstructured":"C.-Y. Hsieh, C.-L. Li, C.-k. Yeh, H. Nakhost, Y. Fujii, A. Ratner, R. Krishna, C.-Y. Lee, T. Pfister, Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes, in: Findings of the Association for Computational Linguistics: ACL 2023, 2023, pp. 8003\u20138017.","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"10.1016\/j.knosys.2026.116606_b9","series-title":"Distillm: Towards streamlined distillation for large language models","author":"Ko","year":"2024"},{"key":"10.1016\/j.knosys.2026.116606_b10","series-title":"International Conference on Machine Learning","first-page":"10421","article-title":"Specializing smaller language models towards multi-step reasoning","author":"Fu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116606_b11","series-title":"Sequence-level knowledge distillation","author":"Kim","year":"2016"},{"key":"10.1016\/j.knosys.2026.116606_b12","series-title":"F-divergence minimization for sequence-level knowledge distillation","author":"Wen","year":"2023"},{"key":"10.1016\/j.knosys.2026.116606_b13","unstructured":"Y. Gu, L. Dong, F. Wei, M. Huang, MiniLLM: Knowledge distillation of large language models, in: The Twelfth International Conference on Learning Representations, 2024."},{"key":"10.1016\/j.knosys.2026.116606_b14","first-page":"23724","article-title":"Multi-level optimal transport for universal cross-tokenizer knowledge distillation on language models","volume":"vol. 39","author":"Cui","year":"2025"},{"key":"10.1016\/j.knosys.2026.116606_b15","doi-asserted-by":"crossref","unstructured":"S. Zhang, X. Zhang, Z. Sun, Y. Chen, J. Xu, Dual-Space Knowledge Distillation for Large Language Models, in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024, pp. 18164\u201318181.","DOI":"10.18653\/v1\/2024.emnlp-main.1010"},{"key":"10.1016\/j.knosys.2026.116606_b16","doi-asserted-by":"crossref","first-page":"24824","DOI":"10.52202\/068431-1800","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116606_b17","doi-asserted-by":"crossref","unstructured":"J. Huang, K.C.-C. Chang, Towards Reasoning in Large Language Models: A Survey, in: Findings of the Association for Computational Linguistics: ACL 2023, 2023, pp. 1049\u20131065.","DOI":"10.18653\/v1\/2023.findings-acl.67"},{"key":"10.1016\/j.knosys.2026.116606_b18","series-title":"Large language models are reasoning teachers","author":"Ho","year":"2022"},{"key":"10.1016\/j.knosys.2026.116606_b19","doi-asserted-by":"crossref","unstructured":"L. Ranaldi, A. Freitas, Aligning large and small language models via chain-of-thought reasoning, in: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), 2024, pp. 1812\u20131827.","DOI":"10.18653\/v1\/2024.eacl-long.109"},{"key":"10.1016\/j.knosys.2026.116606_b20","series-title":"A comprehensive survey of hallucination mitigation techniques in large language models","author":"Tonmoy","year":"2024"},{"key":"10.1016\/j.knosys.2026.116606_b21","series-title":"Lightpaff: A two-stage distillation framework for pre-training and fine-tuning","author":"Song","year":"2020"},{"key":"10.1016\/j.knosys.2026.116606_b22","series-title":"Mixkd: Towards efficient distillation of large-scale language models","author":"Liang","year":"2020"},{"key":"10.1016\/j.knosys.2026.116606_b23","series-title":"Tinybert: Distilling bert for natural language understanding","author":"Jiao","year":"2019"},{"key":"10.1016\/j.knosys.2026.116606_b24","series-title":"Patient knowledge distillation for bert model compression","author":"Sun","year":"2019"},{"key":"10.1016\/j.knosys.2026.116606_b25","first-page":"5776","article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume":"33","author":"Wang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116606_b26","unstructured":"F. Wan, X. Huang, D. Cai, X. Quan, W. Bi, S. Shi, Knowledge Fusion of Large Language Models, in: The Twelfth International Conference on Learning Representations."},{"key":"10.1016\/j.knosys.2026.116606_b27","unstructured":"N. Boizard, K. El Haddad, C. HUDELOT, P. Colombo, Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs, Trans. Mach. Learn. Res.."},{"key":"10.1016\/j.knosys.2026.116606_b28","doi-asserted-by":"crossref","unstructured":"Z. Fang, J. Wang, X. Hu, L. Wang, Y. Yang, Z. Liu, Compressing visual-linguistic model via knowledge distillation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 1428\u20131438.","DOI":"10.1109\/ICCV48922.2021.00146"},{"key":"10.1016\/j.knosys.2026.116606_b29","doi-asserted-by":"crossref","unstructured":"C. Yang, Z. An, L. Huang, J. Bi, X. Yu, H. Yang, B. Diao, Y. Xu, Clip-kd: An empirical study of clip model distillation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 15952\u201315962.","DOI":"10.1109\/CVPR52733.2024.01510"},{"key":"10.1016\/j.knosys.2026.116606_b30","volume":"vol. 338","author":"Villani","year":"2009"},{"key":"10.1016\/j.knosys.2026.116606_b31","first-page":"2292","article-title":"Lightspeed computation of optimal transport","volume":"26","author":"Distances","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116606_b32","article-title":"Towards revealing the mystery behind chain of thought: a theoretical perspective","volume":"36","author":"Feng","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116606_b33","series-title":"Stanford alpaca: An instruction-following LLaMA model","author":"Taori","year":"2023"},{"key":"10.1016\/j.knosys.2026.116606_b34","series-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","first-page":"5085","article-title":"Super-NaturalInstructions: Generalization via declarative instructions on 1600+ NLP tasks","author":"Wang","year":"2022"},{"key":"10.1016\/j.knosys.2026.116606_b35","doi-asserted-by":"crossref","unstructured":"Y. Chen, Y. Liu, L. Chen, Y. Zhang, DialogSum: A Real-Life Scenario Dialogue Summarization Dataset, in: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 2021, pp. 5062\u20135074.","DOI":"10.18653\/v1\/2021.findings-acl.449"},{"issue":"8","key":"10.1016\/j.knosys.2026.116606_b36","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"10.1016\/j.knosys.2026.116606_b37","series-title":"Tinyllama: An open-source small language model","author":"Zhang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116606_b38","series-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"10.1016\/j.knosys.2026.116606_b39","series-title":"Qwen2. 5 technical report","author":"Yang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116606_b40","series-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"10.1016\/j.knosys.2026.116606_b41","unstructured":"C.-Y. Lin, Rouge: A package for automatic evaluation of summaries, in: Text Summarization Branches Out, 2004, pp. 74\u201381."},{"key":"10.1016\/j.knosys.2026.116606_b42","series-title":"Distilling reasoning capabilities into smaller language models","author":"Shridhar","year":"2022"},{"key":"10.1016\/j.knosys.2026.116606_b43","series-title":"Proceedings of the 31st International Conference on Computational Linguistics","first-page":"9074","article-title":"Enhancing the reasoning capabilities of small language models via solution guidance fine-tuning","author":"Bi","year":"2025"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126013328?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126013328?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T14:48:32Z","timestamp":1789310912000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126013328"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":43,"alternative-id":["S0950705126013328"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116606","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Discord: Enhancing knowledge distillation via cross-chain of thought and optimal transport alignment between models with different tokenizers","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116606","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116606"}}