{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:27:32Z","timestamp":1770845252997,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342764","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"6383-6390","source":"Crossref","is-referenced-by-count":0,"title":["Learning Preference Distributions: A Label-Side Paradigm for Explainable Reward Models"],"prefix":"10.1109","author":[{"given":"Shikai","family":"Chen","sequence":"first","affiliation":[{"name":"Southeast University,School of Computer Science and Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Yuan","sequence":"additional","affiliation":[{"name":"AI Lab, Lenovo Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[{"name":"AI Lab, Lenovo Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongchao","family":"Shi","sequence":"additional","affiliation":[{"name":"AI Lab, Lenovo Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianping","family":"Fan","sequence":"additional","affiliation":[{"name":"AI Lab, Lenovo Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Geng","sequence":"additional","affiliation":[{"name":"Southeast University,School of Computer Science and Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Rui","sequence":"additional","affiliation":[{"name":"Southeast University,School of Computer Science and Engineering,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"27 730","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":"ref3","article-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","author":"Bai","year":"2022","journal-title":"arXiv preprint arXiv:2204.05862"},{"key":"ref4","article-title":"Quantile regression for distributional reward models in rlhf","author":"Dorka","year":"2024","journal-title":"arXiv preprint arXiv:2409.10164"},{"key":"ref5","article-title":"Uncertainty-aware reward model: Teaching reward models to know what is unknown","author":"Lou","year":"2024","journal-title":"arXiv preprint arXiv:2410.00847"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2545658"},{"key":"ref7","article-title":"Plug and play language models: A simple approach to controlled text generation","author":"Dathathri","year":"2019","journal-title":"arXiv preprint arXiv:1912.02164"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref9","first-page":"53 728","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","article-title":"Nemotron-4 340b technical report","author":"Adler","year":"2024","journal-title":"arXiv preprint arXiv:2406.11704"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.620"},{"key":"ref12","article-title":"Helpsteer2-preference: Complementing ratings with preferences","author":"Wang","year":"2024"},{"key":"ref13","article-title":"Helpsteer2: Open-source dataset for training top-performing reward models","author":"Wang","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2689998"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/515"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/99"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01400"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1061"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2947040"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015256"},{"key":"ref21","article-title":"Inf-orm-llama3.1-70b","author":"Minghao Yang","year":"2024"},{"key":"ref22","article-title":"Skywork-reward: Bag of tricks for reward modeling in llms","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2410.18451"},{"key":"ref23","article-title":"The biggen bench: A principled benchmark for fine-grained evaluation of language models with language models","author":"Kim","year":"2024"},{"key":"ref24","article-title":"Rewardbench: Evaluating reward models for language modeling","author":"Lambert","year":"2024"},{"key":"ref25","article-title":"Lmsys-chatbot arena human preference predictions, 2024a","author":"Chiang","year":"2024"},{"key":"ref26","article-title":"Rm-bench: Benchmarking reward models of language models with subtlety and style","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2410.16184"}],"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\/11342764.pdf?arnumber=11342764","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:50:18Z","timestamp":1770843018000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342764\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342764","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}