{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T05:47:49Z","timestamp":1767678469743,"version":"3.48.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/aiccsa66935.2025.11315280","type":"proceedings-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:35:55Z","timestamp":1767638155000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["CAKD: A Confidence-Aware Knowledge Distillation Approach for Building Compact and Efficient LLMs"],"prefix":"10.1109","author":[{"given":"Mohammad Basheer","family":"Kotit","sequence":"first","affiliation":[{"name":"Qatar University,Doha,Qatar"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Omama","family":"Hamad","sequence":"additional","affiliation":[{"name":"Qatar University,Doha,Qatar"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khaled","family":"Shaban","sequence":"additional","affiliation":[{"name":"Qatar University,Doha,Qatar"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Hamdi","sequence":"additional","affiliation":[{"name":"MSA University,Cairo,Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"ref3","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"ref5","article-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"Lewis","year":"2019","journal-title":"arXiv preprint arXiv:1910.13461"},{"key":"ref6","first-page":"11328","article-title":"Pegasus: Pre-training with extracted gap-sentences for abstractive summarization","volume-title":"International Conference on Machine Learning","author":"Zhang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1387"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.552"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref12","article-title":"Normkd: Normalized logits for knowledge distillation","author":"Chi","year":"2023","journal-title":"arXiv preprint arXiv:2308.00520"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.207"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.31"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.102"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.189"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.342"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.587"},{"key":"ref20","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv preprint arXiv:1910.01108"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.633"},{"key":"ref23","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":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.468"},{"key":"ref26","first-page":"3956","article-title":"Analyzing uncertainty in neural machine translation","volume-title":"International Conference on Machine Learning","author":"Ott"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.508"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.325"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.102"},{"key":"ref30","article-title":"Dailydialog: A manually labelled multi-turn dialogue dataset","author":"Li","year":"2017","journal-title":"arXiv preprint arXiv:1710.03957"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1205"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1028"},{"key":"ref33","article-title":"Teaching machines to read and comprehend","volume":"28","author":"Hermann","year":"2015","journal-title":"Advances in neural information processing systems"},{"article-title":"Stanford alpaca: An instructionfollowing llama model","year":"2023","author":"Taori","key":"ref34"},{"key":"ref35","article-title":"Instruction tuning with gpt-4","author":"Peng","year":"2023","journal-title":"arXiv preprint arXiv:2304.03277"},{"key":"ref36","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2302.13971"},{"key":"ref37","article-title":"Pre-trained summarization distillation","author":"Shleifer","year":"2020","journal-title":"arXiv preprint arXiv:2010.13002"},{"key":"ref38","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"article-title":"Bertscore: Evaluating text generation with bert","volume-title":"International Conference on Learning Representations","author":"Zhang","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1205"}],"event":{"name":"2025 IEEE\/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)","start":{"date-parts":[[2025,10,19]]},"location":"Doha, Qatar","end":{"date-parts":[[2025,10,22]]}},"container-title":["2025 IEEE\/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11315137\/11315140\/11315280.pdf?arnumber=11315280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T05:44:54Z","timestamp":1767678294000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11315280\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/aiccsa66935.2025.11315280","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}