{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T21:20:47Z","timestamp":1782854447417,"version":"3.54.5"},"reference-count":57,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U25A20539"],"award-info":[{"award-number":["U25A20539"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134297","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T00:02:27Z","timestamp":1781827347000},"page":"134297","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["DDPT: Enhancing complex reasoning in large language models via distillation and dynamic prompt tuning"],"prefix":"10.1016","volume":"698","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1331-9868","authenticated-orcid":false,"given":"Ge","family":"Teng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6399-292X","authenticated-orcid":false,"given":"Wenxiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sinan","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7604-1410","authenticated-orcid":false,"given":"Liang","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0735-8454","authenticated-orcid":false,"given":"Xiang","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6122-0574","authenticated-orcid":false,"given":"Peng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuesong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaowu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134297_bib0005","author":"Zhou"},{"key":"10.1016\/j.neucom.2026.134297_bib0010","author":"Zhao"},{"key":"10.1016\/j.neucom.2026.134297_bib0015","series-title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22","first-page":"5436","article-title":"A survey of vision-language pre-trained models","author":"Du","year":"2022"},{"key":"10.1016\/j.neucom.2026.134297_bib0020","author":"Han"},{"issue":"3","key":"10.1016\/j.neucom.2026.134297_bib0025","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1038\/s42256-023-00626-4","article-title":"Parameter-efficient fine-tuning of large-scale pre-trained language models","volume":"5","author":"Ding","year":"2023","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134297_bib0030","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","first-page":"3045","article-title":"The power of scale for parameter-efficient prompt tuning","author":"Lester","year":"2021"},{"key":"10.1016\/j.neucom.2026.134297_bib0035","series-title":"International Conference on Learning Representations","article-title":"LoRA: low-rank adaptation of large language models","author":"Hu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134297_bib0040","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"4582","article-title":"Prefix-tuning: optimizing continuous prompts for generation","author":"Li","year":"2021"},{"key":"10.1016\/j.neucom.2026.134297_bib0045","series-title":"Proceedings of the 36th International Conference on Machine Learning, 97 Proceedings of Machine Learning Research","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019"},{"key":"10.1016\/j.neucom.2026.134297_bib0050","series-title":"Proceedings of the 41st International Conference on Machine Learning, ICML\u201924","article-title":"Algorithm of thoughts: enhancing exploration of ideas in large language models","author":"Sel","year":"2024"},{"key":"10.1016\/j.neucom.2026.134297_bib0055","series-title":"Advances in Neural Information Processing Systems, 36","first-page":"75623","article-title":"Universality and limitations of prompt tuning","author":"Wang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134297_bib0060","series-title":"The Twelfth International Conference on Learning Representations","article-title":"When do prompting and prefix-tuning work? A theory of capabilities and limitations","author":"Petrov","year":"2024"},{"key":"10.1016\/j.neucom.2026.134297_bib0065","series-title":"Advances in Neural Information Processing Systems, 35","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022"},{"key":"10.1016\/j.neucom.2026.134297_bib0070","author":"Hinton"},{"issue":"6","key":"10.1016\/j.neucom.2026.134297_bib0075","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: a survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134297_bib0080","series-title":"Advances in Neural Information Processing Systems","article-title":"STaR: bootstrapping reasoning with reasoning","author":"Zelikman","year":"2022"},{"key":"10.1016\/j.neucom.2026.134297_bib0085","author":"Yuan"},{"key":"10.1016\/j.neucom.2026.134297_bib0090","series-title":"ICLR 2024 Workshop on Navigating and Addressing Data Problems for Foundation Models","article-title":"Beyond human data: scaling self-training for problem-solving with language models","author":"Singh","year":"2024"},{"key":"10.1016\/j.neucom.2026.134297_bib0095","series-title":"First Conference on Language Modeling","article-title":"V-STaR: training verifiers for self-taught reasoners","author":"Hosseini","year":"2024"},{"key":"10.1016\/j.neucom.2026.134297_bib0100","series-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","first-page":"9134","article-title":"Active example selection for in-context learning","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134297_bib0105","series-title":"Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures","first-page":"100","article-title":"What makes good in-context examples for GPT-3?","author":"Liu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134297_bib0110","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","first-page":"1","article-title":"BitFit: simple parameter-efficient fine-tuning for transformer-based masked language-models","author":"Ben Zaken","year":"2022"},{"key":"10.1016\/j.neucom.2026.134297_bib0115","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"4884","article-title":"Parameter-efficient transfer learning with diff pruning","author":"Guo","year":"2021"},{"key":"10.1016\/j.neucom.2026.134297_bib0120","series-title":"Advances in Neural Information Processing Systems, 30","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.neucom.2026.134297_bib0125","author":"Liu"},{"key":"10.1016\/j.neucom.2026.134297_bib0130","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","first-page":"61","article-title":"P-Tuning: prompt tuning can be comparable to fine-tuning across scales and tasks","author":"Liu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134297_bib0135","author":"Liu"},{"key":"10.1016\/j.neucom.2026.134297_bib0140","series-title":"Findings of the Association for Computational Linguistics: ACL 2023","first-page":"6740","article-title":"Residual prompt tuning: improving prompt tuning with residual reparameterization","author":"Razdaibiedina","year":"2023"},{"key":"10.1016\/j.neucom.2026.134297_bib0145","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2022","first-page":"1325","article-title":"Late prompt tuning: a late prompt could be better than many prompts","author":"Liu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134297_bib0150","series-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","first-page":"11033","article-title":"XPrompt: exploring the extreme of prompt tuning","author":"Ma","year":"2022"},{"key":"10.1016\/j.neucom.2026.134297_bib0155","series-title":"Proceedings of the 40th International Conference on Machine Learning, 202, Proceedings of Machine Learning Research","first-page":"26724","article-title":"On the role of attention in prompt-tuning","author":"Oymak","year":"2023"},{"key":"10.1016\/j.neucom.2026.134297_bib0160","author":"Qin"},{"key":"10.1016\/j.neucom.2026.134297_bib0165","doi-asserted-by":"crossref","first-page":"3631","DOI":"10.1109\/TASLP.2024.3430545","article-title":"Exploring universal intrinsic task subspace for few-shot learning via prompt tuning","volume":"32","author":"Qin","year":"2024","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.neucom.2026.134297_bib0170","series-title":"The Twelfth International Conference on Learning Representations","article-title":"Nemesis: normalizing the soft-prompt vectors of vision-language models","author":"Fu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134297_bib0175","series-title":"The Twelfth International Conference on Learning Representations","article-title":"Two-stage LLM fine-tuning with less specialization and more generalization","author":"Wang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134297_bib0180","series-title":"The Twelfth International Conference on Learning Representations","article-title":"DePT: decomposed prompt tuning for parameter-efficient fine-tuning","author":"Shi","year":"2024"},{"key":"10.1016\/j.neucom.2026.134297_bib0185","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129008","article-title":"Soft prompt-tuning for unsupervised domain adaptation via self-supervision","volume":"617","author":"Zhu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134297_bib0190","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2026.133353","article-title":"Say it better: RL-based prompt tuning for enhancing open-vocabulary recognition","volume":"681","author":"Avshalumov","year":"2026","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134297_bib0195","author":"Yang"},{"key":"10.1016\/j.neucom.2026.134297_bib0200","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing","article-title":"Sentence-BERT: sentence embeddings using Siamese BERT-networks","author":"Reimers","year":"2019"},{"key":"10.1016\/j.neucom.2026.134297_bib0205","author":"Cobbe"},{"key":"10.1016\/j.neucom.2026.134297_bib0210","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"9426","article-title":"Math-shepherd: verify and reinforce LLMs step-by-step without human annotations","author":"Wang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134297_bib0215","author":"Touvron"},{"key":"10.1016\/j.neucom.2026.134297_bib0220","author":"Grattafiori"},{"key":"10.1016\/j.neucom.2026.134297_bib0225","author":"Jiang"},{"key":"10.1016\/j.neucom.2026.134297_bib0230","author":"Yang"},{"key":"10.1016\/j.neucom.2026.134297_bib0235","series-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"158","article-title":"Program induction by rationale generation: learning to solve and explain algebraic word problems","author":"Ling","year":"2017"},{"key":"10.1016\/j.neucom.2026.134297_bib0240","author":"Hendrycks"},{"key":"10.1016\/j.neucom.2026.134297_bib0245","author":"Clark"},{"key":"10.1016\/j.neucom.2026.134297_bib0250","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1162\/tacl_a_00370","article-title":"Did aristotle use a laptop? A question answering benchmark with implicit reasoning strategies","volume":"9","author":"Geva","year":"2021","journal-title":"Trans. Assoc. Comput. Linguist. (TACL)"},{"key":"10.1016\/j.neucom.2026.134297_bib0255","series-title":"DeepSeekMath: pushing the limits of mathematical reasoning in open language models","author":"Zhihong","year":"2024"},{"key":"10.1016\/j.neucom.2026.134297_bib0260","series-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"4793","article-title":"On the efficacy of knowledge distillation","author":"Cho","year":"2019"},{"key":"10.1016\/j.neucom.2026.134297_bib0265","series-title":"Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles","article-title":"Efficient memory management for large language model serving with PagedAttention","author":"Kwon","year":"2023"},{"key":"10.1016\/j.neucom.2026.134297_bib0270","series-title":"The Eleventh International Conference on Learning Representations","article-title":"Towards understanding ensemble, knowledge distillation and self-distillation in deep learning","author":"Allen-Zhu","year":"2023"},{"key":"10.1016\/j.neucom.2026.134297_bib0275","author":"Gao"},{"key":"10.1016\/j.neucom.2026.134297_bib0280","author":"Wang"},{"key":"10.1016\/j.neucom.2026.134297_bib0285","series-title":"ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"18587","article-title":"DDPT: distillation and dynamic prompt tuning for improving complex reasoning in large language models","author":"Teng","year":"2026"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226016954?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226016954?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T20:23:25Z","timestamp":1782851005000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226016954"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":57,"alternative-id":["S0925231226016954"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134297","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DDPT: Enhancing complex reasoning in large language models via distillation and dynamic prompt tuning","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134297","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":"134297"}}