{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:46:00Z","timestamp":1770846360038,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002642","name":"Korea University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002642","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11343731","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"6365-6370","source":"Crossref","is-referenced-by-count":0,"title":["KiC: Keyword-inspired Cascade for Cost-Efficient Text Generation with LLMs"],"prefix":"10.1109","author":[{"given":"Woo-Chan","family":"Kim","sequence":"first","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji-Hoon","family":"Park","sequence":"additional","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seong-Whan","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.abq1158"},{"key":"ref2","article-title":"PaLM 2 Technical Report","author":"Anil","year":"2023"},{"key":"ref3","article-title":"FrugalGPT: How to use large language models while reducing cost and improving performance","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Chen"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.756"},{"key":"ref5","article-title":"Prompting GPT-3 to be reliable","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Si"},{"key":"ref6","article-title":"Can LLMs express their uncertainty? An empirical evaluation of confidence elicitation in LLMs","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Xiong"},{"key":"ref7","article-title":"Self-Consistency improves chain of thought reasoning in language models","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref8","article-title":"Large language model cascades with mixture of thoughts representations for cost-efficient reasoning","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Yue"},{"key":"ref9","first-page":"24824","article-title":"Chain-of-Thought prompting elicits reasoning in large language models","volume-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Wei"},{"key":"ref10","article-title":"Program of Thoughts Prompting: Disentangling computation from reasoning for numerical reasoning tasks","author":"Chen","year":"2023","journal-title":"Trans. Mach. Learning Research"},{"key":"ref11","article-title":"Universal self-consistency for large language models","volume-title":"Int. Conf. Mach. Learn. Workshop. (ICMLW)","author":"Chen"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001490000022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.06.014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635825"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2975848"},{"key":"ref16","article-title":"Self-refine: Iterative refinement with self-feedback","volume-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Madaan"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00614"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2000.902945"},{"key":"ref19","article-title":"Language models (mostly) know what they know","author":"Kadavath","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/1620754.1620758"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref23","article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Zhang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref25","article-title":"Measuring massive multitask language understanding","volume-title":"Int. Conf. Learn. Represent. (ICLR)","author":"Hendrycks"},{"key":"ref26","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11343731.pdf?arnumber=11343731","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:53:16Z","timestamp":1770843196000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11343731\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11343731","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}