{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:51:18Z","timestamp":1783439478454,"version":"3.54.6"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Culture, Sports and Tourism R&D Program through the Korea Creative Content Agency","award":["R2022020070"],"award-info":[{"award-number":["R2022020070"]}]},{"DOI":"10.13039\/501100003561","name":"Ministry of Culture, Sports and Tourism in 2022 (Project Name: Development of artificial intelligence-based game simulation technology to support online game content production","doi-asserted-by":"publisher","award":["R2022020070"],"award-info":[{"award-number":["R2022020070"]}],"id":[{"id":"10.13039\/501100003561","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3403426","type":"journal-article","created":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T17:28:15Z","timestamp":1716226095000},"page":"72578-72587","source":"Crossref","is-referenced-by-count":12,"title":["Discrete Prompt Compression With Reinforcement Learning"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2643-9081","authenticated-orcid":false,"given":"Hoyoun","family":"Jung","sequence":"first","affiliation":[{"name":"School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7732-0817","authenticated-orcid":false,"given":"Kyung-Joong","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Integrated Technology, Gwangju Institute of Science and Technology, Gwangju, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Finetuned language models are zero-shot learners","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wei"},{"key":"ref2","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ouyang"},{"key":"ref3","article-title":"Multitask prompted training enables zero-shot task generalization","volume-title":"Proc. 10th Int. Conf. Learn. Represent. (ICLR)","author":"Sanh"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.412"},{"key":"ref5","article-title":"Learning to compress prompts with gist tokens","author":"Mu","year":"2023","journal-title":"arXiv:2304.08467"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.232"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref8","article-title":"Unlocking context constraints of LLMs: Enhancing context efficiency of LLMs with self-information-based content filtering","author":"Li","year":"2023","journal-title":"arXiv:2304.12102"},{"key":"ref9","first-page":"1","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Sutton"},{"key":"ref10","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.20"},{"key":"ref12","article-title":"GPT understands, too","author":"Liu","year":"2021","journal-title":"arXiv:2103.10385"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.277"},{"key":"ref15","article-title":"Large language models are human-level prompt engineers","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.222"},{"key":"ref17","article-title":"TEMPERA: Test-time prompt editing via reinforcement learning","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1503"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.452"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1158"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/1073445.1073465"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.90"},{"key":"ref23","first-page":"485","article-title":"Contextual multi-armed bandits","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Lu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.498"},{"key":"ref26","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref27","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.460"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.167"},{"key":"ref30","article-title":"Self-instruct: Aligning language models with self-generated instructions","author":"Wang","year":"2022","journal-title":"arXiv:2212.10560"},{"key":"ref31","volume-title":"Stanford Alpaca: An Instruction-Following Llama Model","author":"Taori","year":"2023"},{"issue":"8","key":"ref32","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref33","article-title":"Scaling instruction-finetuned language models","author":"Won Chung","year":"2022","journal-title":"arXiv:2210.11416"},{"key":"ref34","volume-title":"Natural Language Processing With Python: Analyzing Text With the Natural Language Toolkit","author":"Bird","year":"2009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.340"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2305016120"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3587368"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.newsum-1.1"},{"key":"ref39","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref40","article-title":"The Falcon series of open language models","author":"Almazrouei","year":"2023","journal-title":"arXiv:2311.16867"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10535182.pdf?arnumber=10535182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T04:27:38Z","timestamp":1716870458000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10535182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3403426","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}