{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T04:38:58Z","timestamp":1780634338502,"version":"3.54.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100012352","name":"Universit\u00e0 degli Studi di Milano","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012352","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,25]]},"DOI":"10.1109\/fllm67465.2025.11391029","type":"proceedings-article","created":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T20:55:46Z","timestamp":1771534546000},"page":"910-915","source":"Crossref","is-referenced-by-count":1,"title":["Tuning LLM-Based Advisors for the Common Good: The Case for Direct Preference Optimization"],"prefix":"10.1109","author":[{"given":"Lara","family":"Mauri","sequence":"first","affiliation":[{"name":"Università Degli Studi di Milano,Department of Computer Science,Milan,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gohar","family":"Sargsyan","sequence":"additional","affiliation":[{"name":"Tata Consultancy Services, Europe"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ernesto","family":"Damiani","sequence":"additional","affiliation":[{"name":"Università Degli Studi di Milano,Department of Computer Science,Milan,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780198857815.013.18"},{"key":"ref4","article-title":"Rl is neither a panacea nor a mirage: Understanding supervised vs. reinforcement learning fine-tuning for llms","author":"Jin","year":"2025"},{"key":"ref5","article-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-industry.19"},{"key":"ref7","article-title":"Reward model ensembles help mitigate overoptimization","author":"Coste","year":"2023"},{"key":"ref8","article-title":"Do larger language models imply better generalization? a pretraining scaling law for implicit reasoning","volume-title":"ICML 2025 Workshop on Methods and Opportunities at Small Scale","author":"Wang"},{"key":"ref9","article-title":"Self-critiquing models for assisting human evaluators","author":"Saunders","year":"2022"},{"key":"ref10","article-title":"Constitutional ai: Harmlessness from ai feedback","author":"Bai","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-025-00797-3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CSR64739.2025.11130036"},{"key":"ref13","article-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","author":"Bai","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jisa.2017.10.006"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1111\/nyas.15007"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3770749"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.484"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3458754"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.297"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.148"}],"event":{"name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","location":"Vienna, Austria","start":{"date-parts":[[2025,11,25]]},"end":{"date-parts":[[2025,11,28]]}},"container-title":["2025 3rd International Conference on Foundation and Large Language Models (FLLM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11390736\/11390873\/11391029.pdf?arnumber=11391029","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T07:12:45Z","timestamp":1771571565000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11391029\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,25]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/fllm67465.2025.11391029","relation":{},"subject":[],"published":{"date-parts":[[2025,11,25]]}}}