作者位次 #3/7ACL 2026Poster· Natural Language Processing
B ayesian Social Deduction with Graph-Informed Language Models
Shahab Rahimirad · Guven Gergerli · Lucia Romero · Angela Qian · Matthew Lyle Olson · Simon Stepputtis · Joseph Campbell
摘要
Social reasoning—inferring unobservable beliefs and intentions from partial observations of other agents—remains a challenging task for large language models (LLMs). We evaluate the limits of current reasoning language models in the social deduction game Avalon and find that while the largest mod...