@inproceedings{zeng-etal-2026-lvlms,
    title = "{LVLM}s and Humans Ground Differently in Referential Communication",
    author = "Zeng, Peter  and
      Li, Weiling  and
      Paige, Amie J.  and
      Wang, Zhengxiang  and
      Kaliosis, Panagiotis  and
      Samaras, Dimitris  and
      Zelinsky, Gregory J.  and
      Brennan, Susan  and
      Rambow, Owen",
    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.410/",
    pages = "9061--9087",
    ISBN = "979-8-89176-390-6",
    abstract = "For generative AI agents to partner effectively with human users, the ability to accurately predict human intent is critical. But this ability to collaborate remains limited by a critical deficit: an inability to model common ground. We present a referential communication experiment with a factorial design involving director-matcher pairs (human-human, human-AI, AI-human, and AI-AI) that interact with multiple turns in repeated rounds to match pictures of objects not associated with any obvious lexicalized labels. We show that LVLMs cannot interactively generate and resolve referring expressions in a way that enables smooth communication, a crucial skill that underlies human language use. We release our corpus of 356 dialogues (89 pairs over 4 rounds each) along with the online pipeline for data collection and the tools for analyzing accuracy, efficiency, and lexical overlap."
}