@inproceedings{sun-etal-2026-generalizing,
    title = "Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models",
    author = "Sun, Lillian  and
      Pawelczyk, Martin  and
      Qi, Zhenting  and
      Kumar, Aounon  and
      Lakkaraju, Himabindu",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.2163/",
    pages = "46625--46647",
    ISBN = "979-8-89176-390-6"
}