@inproceedings{mondal-etal-2025-group,
    title = "Group Preference Alignment: Customizing {LLM} Responses from In-Situ Conversations Only When Needed",
    author = "Mondal, Ishani  and
      Stokes, Jack W.  and
      Jauhar, Sujay Kumar  and
      Yang, Longqi  and
      Wan, Mengting  and
      Xu, Xiaofeng  and
      Song, Xia  and
      Boyd-Graber, Jordan Lee  and
      Neville, Jennifer",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.56/",
    pages = "825--849",
    ISBN = "979-8-89176-333-3",
    abstract = "LLMs often fail to meet specialized needs of distinct user groups due to their one-size-fits-all approach, and there is limited understanding of what personalization each group expects.To address this, we propose GPA a group-aware personalization framework that captures context-specific preference variations and steers LLMs accordingly.Our approach involves: (1) Group-Aware Preference Extraction, which distills divergent preferences from real-world conversation logs into interpretable rubrics, and (2) Tailored Response Generation, using (a) GPA-CT, which adapts responses using learnt rubrics, and (b) GPA-FT, which finetunes models using rubric-guided synthetic data.Automatic and Human evaluations confirm that GPA improves group alignment without compromising perfomance on standard instruction-following benchmarks."
}