{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T06:59:00Z","timestamp":1774594740704,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,16]]},"DOI":"10.1109\/iciis69028.2026.11450719","type":"proceedings-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:48:40Z","timestamp":1774554520000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing Task-Specific Knowledge Distillation for Dichotomous (Yes\/No) Classification"],"prefix":"10.1109","author":[{"given":"Gobihanath","family":"Balasubramaniam","sequence":"first","affiliation":[{"name":"Sabaragamuwa University of Sri Lanka,Faculty of Computing,Belihuloya,Sri Lanka"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vadivel","family":"Abishethvarman","sequence":"additional","affiliation":[{"name":"Sabaragamuwa University of Sri Lanka,Faculty of Computing,Belihuloya,Sri Lanka"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Senthan","family":"Prasanth","sequence":"additional","affiliation":[{"name":"Memorial University of Newfoundland,Faculty of Science & Engineering,St. John’s,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Banage T. G. S.","family":"Kumara","sequence":"additional","affiliation":[{"name":"Sabaragamuwa University of Sri Lanka,Faculty of Computing,Belihuloya,Sri Lanka"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1086\/288728"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5120\/ijca2017913083"},{"key":"ref3","article-title":"Efficient sentiment analysis and topic modeling in nlp using knowledge distillation and transfer learning","author":"Malki","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.32604\/jqc.2022.026658"},{"key":"ref5","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref6","article-title":"Gemini: a family of highly capable multimodal models","author":"Anil","year":"2023"},{"key":"ref7","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref8","article-title":"Summarization is (almost) dead","author":"Pu","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.246"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01738"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-47240-4_19"},{"key":"ref12","article-title":"Beyond efficiency: A systematic survey of resource-efficient large language models","author":"Bai","year":"2024"},{"key":"ref13","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref15","article-title":"A comprehensive survey on knowledge distillation","author":"Mansourian","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00704"},{"key":"ref17","article-title":"Distilling task-specific knowledge from bert into simple neural networks","author":"Tang","year":"2019"},{"issue":"3","key":"ref18","first-page":"9","article-title":"Random forest vs logistic regression: binary classification for heterogeneous datasets","volume":"1","author":"Kirasich","year":"2018","journal-title":"SMU Data Science Review"},{"issue":"1998","key":"ref19","first-page":"1","article-title":"Linear discriminant analysis-a brief tutorial","volume":"18","author":"Balakrishnama","year":"1998","journal-title":"Institute for Signal and information Processing"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492900002919"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref22","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref23","volume-title":"Large language models (LLMs)","author":"Johnsen","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10515-024-00452-x"},{"key":"ref25","article-title":"A survey on knowledge distillation of large language models","author":"Xu","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3119"},{"key":"ref27","article-title":"Minillm: Knowledge distillation of large language models","author":"Gu","year":"2023"},{"key":"ref28","article-title":"Teacher-student architecture for knowledge distillation: A survey","author":"Hu","year":"2023"},{"key":"ref29","article-title":"Knowledge distillation using frontier open-source llms: Generalizability and the role of synthetic data","author":"Shirgaonkar","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.150"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2764545"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21431"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.nlpcss-1.9"},{"key":"ref34","first-page":"5776","article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pretrained transformers","volume":"33","author":"Wang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01184"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366913"},{"key":"ref39","article-title":"Rethinking kullback-leibler divergence in knowledge distillation for large language models","author":"Wu","year":"2024"}],"event":{"name":"2025 IEEE 19th International Conference on Industrial and Information Systems (ICIIS)","location":"Peradeniya, Sri Lanka","start":{"date-parts":[[2026,1,16]]},"end":{"date-parts":[[2026,1,17]]}},"container-title":["2025 IEEE 19th International Conference on Industrial and Information Systems (ICIIS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11450556\/11450558\/11450719.pdf?arnumber=11450719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T05:27:58Z","timestamp":1774589278000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11450719\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,16]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/iciis69028.2026.11450719","relation":{},"subject":[],"published":{"date-parts":[[2026,1,16]]}}}