{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:09:07Z","timestamp":1761894547927,"version":"build-2065373602"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11208943","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Advancing Safe Language Generation: Exploring Alternative Constrained RLHF"],"prefix":"10.1109","author":[{"given":"Fanyu","family":"Meng","sequence":"first","affiliation":[{"name":"China Mobile Research Institute,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixin","family":"Bai","sequence":"additional","affiliation":[{"name":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanming","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Huo","sequence":"additional","affiliation":[{"name":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boyan","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University,School of Intelligence Science and Technology,Suzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Yang","sequence":"additional","affiliation":[{"name":"China Mobile (Suzhou) Software Technology Co., Ltd.,Suzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"Nanjing University,State Key Laboratory for Novel Software Technology,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2024","key":"ref1","article-title":"Gpt-4o system card"},{"year":"2024","key":"ref2","article-title":"Claude-3.5-sonnet"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3635636.3656201"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.171"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.341"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICEIB61477.2024.10602608"},{"article-title":"Safedialbench: A fine-grained safety benchmark for large language models in multi-turn dialogues with diverse jailbreak attacks","year":"2025","author":"Cao","key":"ref7"},{"key":"ref8","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"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref9"},{"article-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","year":"2022","author":"Bai","key":"ref10"},{"article-title":"Safe RLHF: Safe reinforcement learning from human feedback","volume-title":"The Twelfth International Conference on Learning Representations","author":"Dai","key":"ref11"},{"article-title":"Confronting reward model overoptimization with constrained RLHF","volume-title":"The Twelfth International Conference on Learning Representations","author":"Moskovitz","key":"ref12"},{"article-title":"Bi-factorial preference optimization: Balancing safety-helpfulness in language models","year":"2024","author":"Zhang","key":"ref13"},{"key":"ref14","first-page":"84350","article-title":"One-shot safety alignment for large language models via optimal dualization","volume":"37","author":"Huang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Secrets of rlhf in large language models part i: Ppo","year":"2023","author":"Zheng","key":"ref15"},{"issue":"1","key":"ref16","first-page":"2","article-title":"Benchmarking safe exploration in deep reinforcement learning","volume":"7","author":"Ray","year":"2019"},{"article-title":"Causal information prioritization for efficient reinforcement learning","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Cao","key":"ref17"},{"key":"ref18","first-page":"15338","article-title":"First order constrained optimization in policy space","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/520"},{"issue":"167","key":"ref20","first-page":"1","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2018","journal-title":"Journal of Machine Learning Research"},{"article-title":"Opt: Open pre-trained transformer language models","year":"2022","author":"Zhang","key":"ref21"},{"issue":"9","key":"ref22","article-title":"Stanford alpaca: an instruction-following llama model (2023)","volume":"1","author":"Taori","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00321"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00266"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.441"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.234"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.165"},{"article-title":"A framework for few-shot language model evaluation","year":"2024","author":"Gao","key":"ref29"},{"article-title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","year":"2022","author":"Srivastava","key":"ref30"},{"key":"ref31","first-page":"46595","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","volume":"36","author":"Zheng","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","article-title":"Beavertails: Towards improved safety alignment of llm via a human-preference dataset","volume":"36","author":"Ji","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11208943.pdf?arnumber=11208943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:30:16Z","timestamp":1761888616000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11208943\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11208943","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}