@inproceedings{ryan-etal-2025-synthesizeme,
    title = "{S}ynthesize{M}e! Inducing Persona-Guided Prompts for Personalized Reward Models in {LLM}s",
    author = "Ryan, Michael J  and
      Shaikh, Omar  and
      Bhagirath, Aditri  and
      Frees, Daniel  and
      Held, William Barr  and
      Yang, Diyi",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.397/",
    pages = "8045--8078",
    ISBN = "979-8-89176-251-0",
    abstract = "Recent calls for pluralistic alignment of Large Language Models (LLMs) encourage adapting models to diverse user preferences. However, most prior work on personalized reward models heavily rely on additional identity information, such as demographic details or a predefined set of preference categories. To this end, we introduce SynthesizeMe, an approach to inducing synthetic user personas from user interactions for personalized reward modeling. SynthesizeMe first generates and verifies reasoning to explain user preferences, then induces synthetic user personas from that reasoning, and finally filters to informative prior user interactions in order to build personalized prompts for a particular user. We show that using SynthesizeMe induced prompts improves personalized LLM-as-a-judge accuracy by 4.4{\%} on Chatbot Arena. Combining SynthesizeMe derived prompts with a reward model achieves top performance on PersonalRewardBench: a new curation of user-stratified interactions with chatbots collected from 854 users of Chatbot Arena and PRISM."
}