@inproceedings{ghazaryan-donmez-2026-better,
    title = "Better Reward Models Are Not Always Less Biased: Social Alignment Beyond Standard Reward Benchmarks",
    author = {Ghazaryan, Gayane  and
      D{\"o}nmez, Esra},
    editor = "Xu, Shanshan  and
      T.Y.S.S., Santosh  and
      Kurniawan, Kemal  and
      Peng, Siyao  and
      Wallbridge, Sarenne  and
      Koto, Fajri  and
      Dziri, Nouha  and
      Plank, Barbara",
    booktitle = "Proceedings of the First Workshop on Pluralistic {AI} {NLP}: Diversity-aware, Sociotechnical, Responsible Alignment ({PANDORA} 2026)",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.pandora-1.8/",
    pages = "149--168",
    ISBN = "979-8-89176-484-2"
}