{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:27:54Z","timestamp":1774420074560,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888451","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Small Model Performance in Educational Classification Tasks through Knowledge Distillation"],"prefix":"10.1109","author":[{"given":"Haoxin","family":"Xu","sequence":"first","affiliation":[{"name":"East China Normal University,Shanghai Institute of AI for Education,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changyong","family":"Qi","sequence":"additional","affiliation":[{"name":"East China Normal University,Shanghai Institute of AI for Education,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingqian","family":"Jiang","sequence":"additional","affiliation":[{"name":"East China Normal University,Department of Education Information Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai International Studies University,The School of Journalism and Communication,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longwei","family":"Zheng","sequence":"additional","affiliation":[{"name":"City University of Macau,School of Education,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqing","family":"Gu","sequence":"additional","affiliation":[{"name":"East China Normal University,Department of Education Information Technology,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.33225\/jbse\/17.16.324"},{"key":"ref3","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"ref4","article-title":"Ask me anything: A simple strategy for prompting language models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Arora"},{"key":"ref5","article-title":"Revisiting few-sample bert fine-tuning","author":"Zhang","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref7","article-title":"Learn from model beyond fine-tuning: A survey","author":"Zheng","year":"2023"},{"key":"ref8","article-title":"Chatgpt-3.5","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.603"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.246"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.307"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.americasnlp-1.24"},{"key":"ref14","article-title":"Knowledge distillation of llm for automatic scoring of science education assessments","author":"Latif","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3428519"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1145\/3699518","article-title":"Survey on knowledge distillation for large language models: Methods, evaluation, and application","author":"Yang","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.341"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01065"},{"key":"ref20","article-title":"A survey on knowledge distillation of large language models","author":"Xu","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.semeval-1.226"},{"key":"ref22","article-title":"Self-supervised knowledge distillation for few-shot learning","author":"Rajasegaran","year":"2020"},{"key":"ref23","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","article-title":"Reasoning with large language models, a survey","author":"Plaat","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.441"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"ref27","first-page":"48 573","article-title":"Knowledge-augmented reasoning distillation for small language models in knowledge-intensive tasks","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Kang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657824"},{"key":"ref29","article-title":"Gpt-4 technical report","author":"Achiam","year":"2024"},{"key":"ref30","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref32","first-page":"4654","article-title":"The TalkMoves dataset: K-12 mathematics lesson transcripts annotated for teacher and student discursive moves","volume-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference","author":"Suresh"},{"key":"ref33","article-title":"Gpt-4o","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-019-6413-7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2017.01454"},{"key":"ref36","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref37","first-page":"1275","article-title":"Bigger data or fairer data?: augmenting bert via active sampling for educational text classification","volume-title":"International Conference on Computational Linguistics 2022","author":"Sha"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/info15060345"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888451.pdf?arnumber=10888451","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:15Z","timestamp":1774416375000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888451\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888451","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}