作者位次 #3/7ACL 2026Findings· Findings of ACL
P syche P ass: Calibrating LLM Therapeutic Competence via Trajectory-Anchored Tournaments
Zhuang Chen · Dazhen Wan · Zhangkai Zheng · Guanqun Bi · Xiyao Xiao · Binghang Li · Minlie Huang
摘要
While large language models show promise in mental healthcare, evaluating their therapeutic competence remains challenging due to the unstructured and longitudinal nature of counseling. We argue that current evaluation paradigms suffer from an unanchored defect, leading to two forms of instabilit...