@inproceedings{shen-etal-2025-micro,
    title = "{M}i{CR}o: Mixture Modeling and Context-aware Routing for Personalized Preference Learning",
    author = "Shen, Jingyan  and
      Yao, Jiarui  and
      Yang, Rui  and
      Sun, Yifan  and
      Luo, Feng  and
      Pan, Rui  and
      Zhang, Tong  and
      Zhao, Han",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.882/",
    pages = "17458--17474",
    ISBN = "979-8-89176-332-6",
    abstract = "Reward modeling is a key step in building safe foundation models when applying reinforcement learning from human feedback (RLHF) to align Large Language Models (LLMs). However, reward modeling based on the Bradley-Terry (BT) model assumes a global reward function, failing to capture the inherently diverse and heterogeneous human preferences. Hence, such oversimplification limits LLMs from supporting personalization and pluralistic alignment. Theoretically, we show that when human preferences follow a mixture distribution of diverse subgroups, a single BT model has an irreducible error. While existing solutions, such as fine-grained annotations via prompting or structured preference elicitation, help address this issue, they are costly and constrained by predefined attributes, failing to fully capture the richness of human values. In this work, we introduce MiCRo, a two-stage framework that enhances personalized preference learning by leveraging large-scale binary preference datasets without requiring explicit fine-grained annotations. In the first stage, MiCRo employs a mixture of preferences to model diverse human preferences, enabling a flexible representation of diverse value systems. In the second stage, MiCRo integrates an online routing strategy that dynamically adapts mixture weights based on specific context to resolve ambiguity, allowing for efficient and scalable preference adaptation with minimal additional supervision. Experiments on multiple preference datasets demonstrate that MiCRo effectively captures diverse human preferences and significantly improves personalized preference learning on downstream tasks."
}