一作ACL 2026Poster· Natural Language Processing
LVLM s and Humans Ground Differently in Referential Communication
Peter Zeng · Weiling Li · Amie J. Paige · Zhengxiang Wang · Panagiotis Kaliosis · Dimitris Samaras · Gregory Zelinsky · Susan E. Brennan · Owen Rambow
摘要
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 factor...