{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T19:39:09Z","timestamp":1786390749091,"version":"build-2736575974"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation (IITP) funded by the Korea government","award":["IITP-2025-RS-2024-00436857"],"award-info":[{"award-number":["IITP-2025-RS-2024-00436857"]}]},{"name":"Institute of Information & Communications Technology Planning & Evaluation (IITP) funded by the Korea government","award":["RS-2019-II190079"],"award-info":[{"award-number":["RS-2019-II190079"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3713532","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:06:14Z","timestamp":1784145974000},"page":"118580-118590","source":"Crossref","is-referenced-by-count":0,"title":["Negative Contrastive Chain-of-Thought Distillation for Transfer Reasoning Capability to Small Language Models"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1442-0820","authenticated-orcid":false,"given":"Jae-Wook","family":"Han","sequence":"first","affiliation":[{"name":"Korea University","place":["Seoul, Republic of Korea"],"department":["Department of Artificial Intelligence"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3155-1943","authenticated-orcid":false,"given":"Hayoung","family":"Jo","sequence":"additional","affiliation":[{"name":"Korea University","place":["Seoul, Republic of Korea"],"department":["Department of Artificial Intelligence"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9597-8171","authenticated-orcid":false,"given":"Jung-Ho","family":"Hong","sequence":"additional","affiliation":[{"name":"Korea University","place":["Seoul, Republic of Korea"],"department":["Department of Artificial Intelligence"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-4996","authenticated-orcid":false,"given":"Seong-Whan","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University","place":["Seoul, Republic of Korea"],"department":["Department of Artificial Intelligence"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey of large language models","author":"Xin Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2176"},{"key":"ref3","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv:2001.08361"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00704"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3554586"},{"issue":"240","key":"ref7","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Brown"},{"key":"ref9","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.32"},{"key":"ref12","first-page":"1","article-title":"Emergent abilities of large language models","author":"Wei","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"issue":"70","key":"ref13","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.454"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.830"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3591266"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29821"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.21"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3571497"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.153"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3494054"},{"key":"ref23","first-page":"10421","article-title":"Specializing smaller language models towards multi-step reasoning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Fu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"ref25","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref26","article-title":"Automatic chain of thought prompting in large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106594"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00797"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.63317\/36yfg5x3ycgy"},{"key":"ref30","first-page":"3439","article-title":"LLMs can find mathematical reasoning mistakes by pedagogical chain-of-thought","volume-title":"Proc. Int. Joint Conf. Artif. Intell. (IJCAI)","author":"Jiang"},{"key":"ref31","article-title":"Constitutional AI: Harmlessness from AI feedback","author":"Bai","year":"2022","journal-title":"arXiv:2212.08073"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.910"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.02.007"},{"key":"ref34","article-title":"Teaching large language models to self-debug","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chen"},{"key":"ref35","article-title":"Generating sequences by learning to self-correct","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Welleck"},{"key":"ref36","first-page":"23694","article-title":"Progressive distillation induces an implicit curriculum","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Panigrahi"},{"key":"ref37","first-page":"31044","article-title":"DistiLLM-2: A contrastive approach boosts the distillation of LLMs","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"267","author":"Ko"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3591056"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.610"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00748"},{"key":"ref41","first-page":"24872","article-title":"DistiLLM: Towards streamlined distillation for large language models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"997","author":"Ko"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17516"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3372568"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6229"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118636"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.185"},{"key":"ref47","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hu"},{"key":"ref48","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv:2110.14168"},{"key":"ref49","first-page":"20785","article-title":"Measuring mathematical problem solving with the MATH dataset","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"1","author":"Hendrycks"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.168"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.92"},{"key":"ref52","first-page":"4149","article-title":"CommonsenseQA: A question answering challenge targeting commonsense knowledge","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol. (NAACL-HLT)","author":"Talmor"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365072.09396"},{"key":"ref55","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref56","article-title":"Mistral 7B","author":"Jiang","year":"2023","journal-title":"arXiv:2310.06825"},{"key":"ref57","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref58","article-title":"Gemma 2: Improving open language models at a practical size","author":"Team","year":"2024","journal-title":"arXiv:2408.00118"},{"key":"ref59","article-title":"The curious case of neural text degeneration","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Holtzman"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.390"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11610983.pdf?arnumber=11610983","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T19:09:24Z","timestamp":1786388964000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11610983\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3713532","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}