{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:16:02Z","timestamp":1774419362392,"version":"3.50.1"},"reference-count":30,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887891","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Online Learning from Strategic Human Feedback in LLM Fine-Tuning"],"prefix":"10.1109","author":[{"given":"Shugang","family":"Hao","sequence":"first","affiliation":[{"name":"Singapore University of Technology and Design,Pillar of Engineering Systems and Design"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingjie","family":"Duan","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design,Pillar of Engineering Systems and Design"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Open and efficient foundation language models","volume":"2302","author":"Touvron","year":"2023"},{"key":"ref2","article-title":"Openassistant conversations-democratizing large language model alignment","volume":"36","author":"K\u00f6pf","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","article-title":"Mechanism design for llm fine-tuning with multiple reward models","author":"Sun","year":"2024"},{"key":"ref4","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback. corr, abs\/2204.05862, 2022a. doi: 10.48550","author":"Bai","year":"2022"},{"key":"ref7","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref8","article-title":"Iterative preference learning from human feedback: Bridging theory and practice for rlhf under kl-constraint","volume-title":"Forty-first International Conference on Machine Learning","author":"Xiong"},{"key":"ref9","article-title":"Truthful aggregation of llms with an application to online advertising","author":"Soumalias","year":"2024"},{"key":"ref10","article-title":"Social choice for ai alignment: Dealing with diverse human feedback","author":"Conitzer","year":"2024"},{"key":"ref11","article-title":"Online prediction with selfish experts","volume":"30","author":"Roughgarden","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","article-title":"Exploratory preference optimization: Harnessing implicit q*-approximation for sample-efficient rlhf","author":"Xie","year":"2024"},{"key":"ref14","article-title":"Value-incentivized preference optimization: A unified approach to online and offline rlhf","author":"Cen","year":"2024"},{"key":"ref15","article-title":"Self-exploring language models: Active preference elicitation for online alignment","author":"Zhang","year":"2024"},{"key":"ref16","article-title":"Optune: Efficient online preference tuning","author":"Chen","year":"2024"},{"key":"ref17","article-title":"Rlhf from heterogeneous feedback via personalization and preference aggregation","volume-title":"ICML 2024 Workshop on Theoretical Foundations of Foundation Models","author":"Park"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672022"},{"key":"ref19","article-title":"Collaborative algorithms for online personalized mean estimation","author":"Asadi","year":"2022","journal-title":"Transactions on Machine Learning Research Journal"},{"key":"ref20","article-title":"Mechanism design for collaborative normal mean estimation","volume":"36","author":"Chen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28843"},{"key":"ref22","first-page":"1883","article-title":"Positive intra-group externalities in facility location","volume-title":"Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems","author":"Wang"},{"key":"ref23","article-title":"Dueling rl: reinforcement learning with trajectory preferences","author":"Pacchiano","year":"2021"},{"key":"ref24","first-page":"3773","article-title":"Human-inthe-loop: Provably efficient preference-based reinforcement learning with general function approximation","volume-title":"International Conference on Machine Learning","author":"Chen"},{"key":"ref25","article-title":"Dpo meets ppo: Reinforced token optimization for rlhf","author":"Zhong","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3465456.3467635"},{"key":"ref27","first-page":"3270","article-title":"No-regret and incentive-compatible online learning","volume-title":"International Conference on Machine Learning","author":"Freeman"},{"key":"ref28","article-title":"Online learning from strategic human feedback in llm fine-tuning","author":"Hao","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.530"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w17-4508"}],"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\/10887891.pdf?arnumber=10887891","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:30Z","timestamp":1774416150000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887891\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887891","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}