{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T18:37:05Z","timestamp":1771267025170,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,2,22]]},"DOI":"10.1145\/3773966.3777945","type":"proceedings-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T17:50:01Z","timestamp":1771264201000},"page":"58-68","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Personality Generation of LLMs at Decoding-time"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4409-5627","authenticated-orcid":false,"given":"Rongxin","family":"Chen","sequence":"first","affiliation":[{"name":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1300-9556","authenticated-orcid":false,"given":"Yunfan","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8856-668X","authenticated-orcid":false,"given":"Yige","family":"Yuan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8319-2681","authenticated-orcid":false,"given":"Bingbing","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2425-1499","authenticated-orcid":false,"given":"Huawei","family":"Shen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2026,2,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. ArXiv","author":"Bai Yuntao","year":"2022","unstructured":"Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova Dassarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, Nicholas Joseph, Saurav Kadavath, John 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 B. Brown, Jack Clark, Sam McCandlish, Chris Olah, Benjamin Mann, and Jared Kaplan. 2022a. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. ArXiv, Vol. abs\/2204.05862 (2022). https:\/\/api.semanticscholar.org\/CorpusID:248118878"},{"key":"e_1_3_2_1_2_1","unstructured":"Yuntao Bai Saurav Kadavath Sandipan Kundu Amanda Askell John Kernion Andy Jones Anna Chen Anna Goldie Azalia Mirhoseini Cameron McKinnon Carol Chen Catherine Olsson Chris Olah Danny Hernandez Dawn Drain Deep Ganguli Dustin Li Eli Tran-Johnson E Perez Jamie Kerr Jared Mueller Jeff Ladish J Landau Kamal Ndousse Kamile Luko\u0161iute Liane Lovitt Michael Sellitto Nelson Elhage Nicholas Schiefer Noemi Mercado Nova Dassarma Robert Lasenby Robin Larson Sam Ringer Scott Johnston Shauna Kravec Sheer El Showk Stanislav Fort Tamera Lanham Timothy Telleen-Lawton Tom Conerly Tom Henighan Tristan Hume Sam Bowman Zac Hatfield-Dodds Benjamin Mann Dario Amodei Nicholas Joseph Sam McCandlish Tom B. Brown and Jared Kaplan. 2022b. Constitutional AI: Harmlessness from AI Feedback. ArXiv Vol. abs\/2212.08073 (2022). https:\/\/api.semanticscholar.org\/CorpusID:254823489"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Nawal Benabbou and Patrice Perny. 2015. Incremental Weight Elicitation for Multiobjective State Space Search. (2015).","DOI":"10.1609\/aaai.v29i1.9362"},{"key":"e_1_3_2_1_4_1","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Pond\u00e9 Jared Kaplan Harrison Edwards Yura Burda Nicholas Joseph Greg Brockman Alex Ray Raul Puri Gretchen Krueger Michael Petrov Heidy Khlaaf Girish Sastry Pamela Mishkin Brooke Chan Scott Gray Nick Ryder Mikhail Pavlov Alethea Power Lukasz Kaiser Mo Bavarian Clemens Winter Phil Tillet Felipe Petroski Such David W. Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William H. Guss Alex Nichol Igor Babuschkin Suchir Balaji Shantanu Jain Andrew Carr Jan Leike Josh Achiam Vedant Misra Evan Morikawa Alec Radford Matthew M. Knight Miles Brundage Mira Murati Katie Mayer Peter Welinder Bob McGrew Dario Amodei Sam McCandlish Ilya Sutskever and Wojciech Zaremba. 2021. Evaluating Large Language Models Trained on Code. ArXiv Vol. abs\/2107.03374 (2021). https:\/\/api.semanticscholar.org\/CorpusID:235755472"},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Learning Representations. https:\/\/api.semanticscholar.org\/CorpusID:273185508","author":"Chen Ruizhe","year":"2024","unstructured":"Ruizhe Chen, Xiaotian Zhang, Meng Luo, Wenhao Chai, and Zuozhu Liu. 2024. PAD: Personalized Alignment of LLMs at Decoding-time. In International Conference on Learning Representations. https:\/\/api.semanticscholar.org\/CorpusID:273185508"},{"key":"e_1_3_2_1_6_1","volume-title":"Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects. ArXiv","author":"Cheng Yuheng","year":"2024","unstructured":"Yuheng Cheng, Ceyao Zhang, Zhengwen Zhang, Xiangrui Meng, Sirui Hong, Wenhao Li, Zihao Wang, Zekai Wang, Feng Yin, Junhua Zhao, and Xiuqiang He. 2024. Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects. ArXiv, Vol. abs\/2401.03428 (2024). https:\/\/api.semanticscholar.org\/CorpusID:266844118"},{"key":"e_1_3_2_1_7_1","volume-title":"Machine Mindset: An MBTI Exploration of Large Language Models. ArXiv","author":"Cui Jiaxi","year":"2023","unstructured":"Jiaxi Cui, Liuzhenghao Lv, Jing Wen, Rongsheng Wang, Jing Tang, Yonghong Tian, and Li Yuan. 2023. Machine Mindset: An MBTI Exploration of Large Language Models. ArXiv, Vol. abs\/2312.12999 (2023). https:\/\/api.semanticscholar.org\/CorpusID:266375150"},{"key":"e_1_3_2_1_8_1","volume-title":"OpenPrompt: An Open-source Framework for Prompt-learning. ArXiv","author":"Ding Ning","year":"1998","unstructured":"Ning Ding, Shengding Hu, Weilin Zhao, Yulin Chen, Zhiyuan Liu, Haitao Zheng, and Maosong Sun. 2021. OpenPrompt: An Open-source Framework for Prompt-learning. ArXiv, Vol. abs\/2111.01998 (2021). https:\/\/api.semanticscholar.org\/CorpusID:241033259"},{"key":"e_1_3_2_1_9_1","volume-title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback. ArXiv","author":"Dubois Yann","year":"2023","unstructured":"Yann Dubois, Xuechen Li, Rohan Taori, Tianyi Zhang, Ishaan Gulrajani, Jimmy Ba, Carlos Guestrin, Percy Liang, and Tatsunori Hashimoto. 2023. AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback. ArXiv, Vol. abs\/2305.14387 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258865545"},{"key":"e_1_3_2_1_10_1","volume-title":"International Joint Conference on Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:267412980","author":"Guo Taicheng","year":"2024","unstructured":"Taicheng Guo, Xiuying Chen, Yaqi Wang, Ruidi Chang, Shichao Pei, N. Chawla, Olaf Wiest, and Xiangliang Zhang. 2024. Large Language Model based Multi-Agents: A Survey of Progress and Challenges. In International Joint Conference on Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:267412980"},{"key":"e_1_3_2_1_11_1","volume-title":"Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI. ArXiv","author":"Harland Hadassah","year":"2024","unstructured":"Hadassah Harland, Richard Dazeley, Peter Vamplew, Hashini Senaratne, Bahareh Nakisa, and Francisco Cruz. 2024. Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI. ArXiv, Vol. abs\/2410.23630 (2024). https:\/\/api.semanticscholar.org\/CorpusID:273707152"},{"key":"e_1_3_2_1_12_1","volume-title":"Towards Reasoning in Large Language Models: A Survey. ArXiv","author":"Huang Jie","year":"2022","unstructured":"Jie Huang and Kevin Chen-Chuan Chang. 2022. Towards Reasoning in Large Language Models: A Survey. ArXiv, Vol. abs\/2212.10403 (2022). https:\/\/api.semanticscholar.org\/CorpusID:254877753"},{"key":"e_1_3_2_1_13_1","volume-title":"Arshit Gupta, Nikolaos Pappas, Saab Mansour, Katrin Kirchoff, and Dan Roth.","author":"Huang James Y.","year":"2024","unstructured":"James Y. Huang, Sailik Sengupta, Daniele Bonadiman, Yi an Lai, Arshit Gupta, Nikolaos Pappas, Saab Mansour, Katrin Kirchoff, and Dan Roth. 2024. DeAL: Decoding-time Alignment for Large Language Models. ArXiv, Vol. abs\/2402.06147 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267616998"},{"key":"e_1_3_2_1_14_1","volume-title":"GPT-4o System Card. ArXiv","author":"Aaron Hurst AI","year":"2024","unstructured":"OpenAI Aaron Hurst, Adam Lerer, Adam P. Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, Aleksander Mkadry, Alex Baker-Whitcomb, Alex Beutel, Alex Borzunov, Alex Carney, Alex Chow, Alexander Kirillov, Alex Nichol, Alex Paino, Alex Renzin, Alexandre Passos, Alexander Kirillov, Alexi Christakis, Alexis Conneau, Ali Kamali, Allan Jabri, Allison Moyer, Allison Tam, and Amadou Crookes et.al. 2024. GPT-4o System Card. ArXiv, Vol. abs\/2410.21276 (2024). https:\/\/api.semanticscholar.org\/CorpusID:273662196"},{"key":"e_1_3_2_1_15_1","volume-title":"Yizhong Wang, Jack Hessel, Luke S. Zettlemoyer, Hannaneh Hajishirzi, Yejin Choi, and Prithviraj Ammanabrolu.","author":"Jang Joel","year":"2023","unstructured":"Joel Jang, Seungone Kim, Bill Yuchen Lin, Yizhong Wang, Jack Hessel, Luke S. Zettlemoyer, Hannaneh Hajishirzi, Yejin Choi, and Prithviraj Ammanabrolu. 2023. Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging. ArXiv, Vol. abs\/2310.11564 (2023). https:\/\/api.semanticscholar.org\/CorpusID:264289231"},{"key":"e_1_3_2_1_16_1","first-page":"15674","volume-title":"Zhang (Eds.)","volume":"37","author":"Jia Feiran","year":"2024","unstructured":"Feiran Jia, Ziyu Ye, Shiyang Lai, Kai Shu, Jindong Gu, Adel Bibi, Ziniu Hu, David Jurgens, James Evans, Philip H.S. Torr, Bernard Ghanem, Guohao Li, Chengxing Xie, and Canyu Chen. 2024. Can Large Language Model Agents Simulate Human Trust Behavior?. In Advances in Neural Information Processing Systems, A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang (Eds.), Vol. 37. Curran Associates, Inc., 15674-15729. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2024\/file\/1cb57fcf7ff3f6d37eebae5becc9ea6d-Paper-Conference.pdf"},{"key":"e_1_3_2_1_17_1","volume-title":"ARGS: Alignment as Reward-Guided Search. ArXiv","author":"Khanov Maxim","year":"2024","unstructured":"Maxim Khanov, Jirayu Burapacheep, and Yixuan Li. 2024. ARGS: Alignment as Reward-Guided Search. ArXiv, Vol. abs\/2402.01694 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267411977"},{"key":"e_1_3_2_1_18_1","first-page":"324","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2025","author":"Kim Hyunwoo","year":"2025","unstructured":"Hyunwoo Kim, Seunghyun Lee, Yongrae Lee, Sohee Kim, Jihyung Han, Yoon Sun, Sangwoo Lee, Hyung Won Cho, and Edward Choi. 2025. Drift: Training-Free Personalization of Large Language Models via Decoding-Time Attribute Composition. In Findings of the Association for Computational Linguistics: EMNLP 2025. Association for Computational Linguistics. https:\/\/aclanthology.org\/2025.findings-emnlp.324"},{"key":"e_1_3_2_1_19_1","volume-title":"Kang Min Yoo, and Minjoon Seo","author":"Kim Sungdong","year":"2023","unstructured":"Sungdong Kim, Sanghwan Bae, Jamin Shin, Soyoung Kang, Donghyun Kwak, Kang Min Yoo, and Minjoon Seo. 2023. Aligning Large Language Models through Synthetic Feedback. ArXiv, Vol. abs\/2305.13735 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258841835"},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:254096365","author":"Leviathan Yaniv","year":"2022","unstructured":"Yaniv Leviathan, Matan Kalman, and Yossi Matias. 2022. Fast Inference from Transformers via Speculative Decoding. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:254096365"},{"key":"e_1_3_2_1_21_1","volume-title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security. ArXiv","author":"Li Yuanchun","year":"2024","unstructured":"Yuanchun Li, Hao Wen, Weijun Wang, Xiangyu Li, Yizhen Yuan, Guohong Liu, Jiacheng Liu, Wenxing Xu, Xiang Wang, Yi Sun, Rui Kong, Yile Wang, Hanfei Geng, Jian Luan, Xuefeng Jin, Zi-Liang Ye, Guanjing Xiong, Fan Zhang, Xiang Li, Mengwei Xu, Zhijun Li, Peng Li, Yang Liu, Yaqiong Zhang, and Yunxin Liu. 2024. Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security. ArXiv, Vol. abs\/2401.05459 (2024). https:\/\/api.semanticscholar.org\/CorpusID:266933252"},{"key":"e_1_3_2_1_22_1","volume-title":"Inferring Preferences from Demonstrations in Multi-objective Reinforcement Learning: A Dynamic Weight-based Approach. ArXiv","author":"Lu Junlin","year":"2023","unstructured":"Junlin Lu, Patrick Mannion, and Karl Mason. 2023. Inferring Preferences from Demonstrations in Multi-objective Reinforcement Learning: A Dynamic Weight-based Approach. ArXiv, Vol. abs\/2304.14115 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258352486"},{"key":"e_1_3_2_1_23_1","volume-title":"Jan Leike, and Ryan J. Lowe.","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke E. Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Francis Christiano, Jan Leike, and Ryan J. Lowe. 2022. Training language models to follow instructions with human feedback. ArXiv, Vol. abs\/2203.02155 (2022). https:\/\/api.semanticscholar.org\/CorpusID:246426909"},{"key":"e_1_3_2_1_24_1","volume-title":"Do LLMs Possess a Personality? Making the MBTI Test an Amazing Evaluation for Large Language Models. ArXiv","author":"Pan Keyu","year":"2023","unstructured":"Keyu Pan and Yawen Zeng. 2023. Do LLMs Possess a Personality? Making the MBTI Test an Amazing Evaluation for Large Language Models. ArXiv, Vol. abs\/2307.16180 (2023). https:\/\/api.semanticscholar.org\/CorpusID:260334342"},{"key":"e_1_3_2_1_25_1","volume-title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model. ArXiv","author":"Rafailov Rafael","year":"1829","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D. Manning, and Chelsea Finn. 2023. Direct Preference Optimization: Your Language Model is Secretly a Reward Model. ArXiv, Vol. abs\/2305.18290 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258959321"},{"key":"e_1_3_2_1_26_1","volume-title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards. ArXiv","author":"Ram\u00e9 Alexandre","year":"2023","unstructured":"Alexandre Ram\u00e9, Guillaume Couairon, Mustafa Shukor, Corentin Dancette, Jean-Baptiste Gaya, Laure Soulier, and Matthieu Cord. 2023. Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards. ArXiv, Vol. abs\/2306.04488 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259096117"},{"key":"e_1_3_2_1_27_1","volume-title":"Proximal Policy Optimization Algorithms. ArXiv","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. ArXiv, Vol. abs\/1707.06347 (2017). https:\/\/api.semanticscholar.org\/CorpusID:28695052"},{"key":"e_1_3_2_1_28_1","volume-title":"Decoding-Time Language Model Alignment with Multiple Objectives. ArXiv","author":"Shi Ruizhe","year":"1885","unstructured":"Ruizhe Shi, Yifang Chen, Yushi Hu, Alisa Liu, Hanna Hajishirzi, Noah A. Smith, and Simon Shaolei Du. 2024. Decoding-Time Language Model Alignment with Multiple Objectives. ArXiv, Vol. abs\/2406.18853 (2024). https:\/\/api.semanticscholar.org\/CorpusID:270764846"},{"key":"e_1_3_2_1_29_1","first-page":"32630","volume-title":"Zhang (Eds.)","volume":"37","author":"Sun Hanshi","year":"2024","unstructured":"Hanshi Sun, Momin Haider, Ruiqi Zhang, Huitao Yang, Jiahao Qiu, Ming Yin, Mengdi Wang, Peter Bartlett, and Andrea Zanette. 2024. Fast Best-of-N Decoding via Speculative Rejection. In Advances in Neural Information Processing Systems, A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang (Eds.), Vol. 37. Curran Associates, Inc., 32630-32652. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2024\/file\/3950f6bf5c2eb7435ecf58eaa85cc8c2-Paper-Conference.pdf"},{"key":"e_1_3_2_1_30_1","volume-title":"Siyu Yuan, Haoran Guo, Jiangjie Chen, Wei Wang, Yanghua Xiao, and Shuchang Zhou.","author":"Wang Xintao","year":"2025","unstructured":"Xintao Wang, Heng Wang, Yifei Zhang, Xinfeng Yuan, Rui Xu, Jen tse Huang, Siyu Yuan, Haoran Guo, Jiangjie Chen, Wei Wang, Yanghua Xiao, and Shuchang Zhou. 2025. CoSER: Coordinating LLM-Based Persona Simulation of Established Roles. ArXiv, Vol. abs\/2502.09082 (2025). https:\/\/api.semanticscholar.org\/CorpusID:276317668"},{"key":"e_1_3_2_1_31_1","volume-title":"Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S. Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, and Ludwig Schmidt.","author":"Wortsman Mitchell","year":"2022","unstructured":"Mitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S. Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, and Ludwig Schmidt. 2022. Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. ArXiv, Vol. abs\/2203.05482 (2022). https:\/\/api.semanticscholar.org\/CorpusID:247362886"},{"key":"e_1_3_2_1_32_1","unstructured":"Kailai Yang Zhiwei Liu Qianqian Xie Jimin Huang Tianlin Zhang and Sophia Ananiadou. 2024a. MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models. In Neural Information Processing Systems. https:\/\/api.semanticscholar.org\/CorpusID:269605800"},{"key":"e_1_3_2_1_33_1","volume-title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment. ArXiv","author":"Yang Rui","year":"2024","unstructured":"Rui Yang, Xiaoman Pan, Feng Luo, Shuang Qiu, Han Zhong, Dong Yu, and Jianshu Chen. 2024b. Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment. ArXiv, Vol. abs\/2402.10207 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267682397"},{"key":"e_1_3_2_1_34_1","volume-title":"A Survey of Large Language Models. ArXiv","author":"Zhao Wayne Xin","year":"1822","unstructured":"Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, Yifan Du, Chen Yang, Yushuo Chen, Z. Chen, Jinhao Jiang, Ruiyang Ren, Yifan Li, Xinyu Tang, Zikang Liu, Peiyu Liu, Jianyun Nie, and Ji rong Wen. 2023. A Survey of Large Language Models. ArXiv, Vol. abs\/2303.18223 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257900969"},{"key":"e_1_3_2_1_35_1","volume-title":"Judging LLM-as-a-judge with MT-Bench and Chatbot Arena. ArXiv","author":"Zheng Lianmin","year":"2023","unstructured":"Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Haotong Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023. Judging LLM-as-a-judge with MT-Bench and Chatbot Arena. ArXiv, Vol. abs\/2306.05685 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259129398"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Zhanhui Zhou Jie Liu Jing Shao Xiangyu Yue Chao Yang Wanli Ouyang and Yu Qiao. 2023. Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:264175263","DOI":"10.18653\/v1\/2024.findings-acl.630"},{"key":"e_1_3_2_1_37_1","volume-title":"Fine-Tuning Language Models from Human Preferences. ArXiv","author":"Ziegler Daniel M.","year":"2019","unstructured":"Daniel M. Ziegler, Nisan Stiennon, Jeff Wu, Tom B. Brown, Alec Radford, Dario Amodei, Paul Christiano, and Geoffrey Irving. 2019. Fine-Tuning Language Models from Human Preferences. ArXiv, Vol. abs\/1909.08593 (2019). https:\/\/api.semanticscholar.org\/CorpusID:202660943"}],"event":{"name":"WSDM '26:The Nineteenth ACM International Conference on Web Search and Data Mining","location":"Boise ID USA","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T17:50:18Z","timestamp":1771264218000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3773966.3777945"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,21]]},"references-count":37,"alternative-id":["10.1145\/3773966.3777945","10.1145\/3773966"],"URL":"https:\/\/doi.org\/10.1145\/3773966.3777945","relation":{},"subject":[],"published":{"date-parts":[[2026,2,21]]},"assertion":[{"value":"2026-02-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}