{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:55:59Z","timestamp":1776880559703,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":9,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Australian Research Council (ARC) Training Centre for Information Resilience","award":["IC200100022"],"award-info":[{"award-number":["IC200100022"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,8]]},"DOI":"10.1145\/3673791.3698411","type":"proceedings-article","created":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T06:24:16Z","timestamp":1733639056000},"page":"236-240","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Optimizing LLMs with Direct Preferences: A Data Efficiency Perspective"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3657-9229","authenticated-orcid":false,"given":"Pietro","family":"Bernardelle","sequence":"first","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7311-3693","authenticated-orcid":false,"given":"Gianluca","family":"Demartini","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Yuntao Bai Andy Jones Kamal Ndousse Amanda Askell Anna Chen Nova Das-Sarma Dawn Drain Stanislav Fort Deep Ganguli Tom Henighan Nicholas Joseph Saurav Kadavath Jackson Kernion Tom Conerly Sheer El-Showk Nelson Elhage Zac Hatfield-Dodds Danny Hernandez Tristan Hume Scott Johnston Shauna Kravec Liane Lovitt Neel Nanda Catherine Olsson Dario Amodei Tom Brown Jack Clark Sam McCandlish Chris Olah Ben Mann and Jared Kaplan. 2022. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. arXiv:2204.05862 [cs.CL]"},{"key":"e_1_3_2_2_2_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_3_2_2_3_1","volume-title":"Deep Reinforcement Learning from Human Preferences. Advances in Neural Information Processing Systems 30","author":"Christiano Paul F","year":"2017","unstructured":"Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep Reinforcement Learning from Human Preferences. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_2_4_1","volume-title":"Ultrafeedback: Boosting language models with high-quality feedback. arXiv preprint arXiv:2310.01377","author":"Cui Ganqu","year":"2023","unstructured":"Ganqu Cui, Lifan Yuan, Ning Ding, Guanming Yao, Wei Zhu, Yuan Ni, Guotong Xie, Zhiyuan Liu, and Maosong Sun. 2023. Ultrafeedback: Boosting language models with high-quality feedback. arXiv preprint arXiv:2310.01377 (2023)."},{"key":"e_1_3_2_2_5_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proc. NAACL-HLT","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proc. NAACL-HLT 2019. Association for Computational Linguistics, Minneapolis, Minnesota, 4171--4186."},{"key":"e_1_3_2_2_6_1","volume-title":"Chanvichet Vong, and ''Teknium''.","author":"Lian Wing","year":"2023","unstructured":"Wing Lian, Bleys Goodson, Eugene Pentland, Austin Cook, Chanvichet Vong, and ''Teknium''. 2023. OpenOrca: An Open Dataset of GPT Augmented FLAN Reasoning Traces. huggingface.co (2023)."},{"key":"e_1_3_2_2_7_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_8_1","first-page":"53728","article-title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","volume":"36","author":"Rafailov Rafael","year":"2023","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct Preference Optimization: Your Language Model is Secretly a Reward Model. Advances in Neural Information Processing Systems 36 (2023), 53728--53741.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_9_1","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric Xing et al. 2024. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems 36 (2024)."}],"event":{"name":"SIGIR-AP 2024: Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","location":"Tokyo Japan","acronym":"SIGIR-AP 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 2024 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673791.3698411","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3673791.3698411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T16:22:47Z","timestamp":1755879767000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673791.3698411"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"references-count":9,"alternative-id":["10.1145\/3673791.3698411","10.1145\/3673791"],"URL":"https:\/\/doi.org\/10.1145\/3673791.3698411","relation":{},"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"2024-12-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}