作者位次 #3/4ACL 2026Findings· Findings of ACL
S ense J udge: Human-Centric Preference-Driven Judgment Framework
Rui Li · Junfeng Liu · Xiangwen Kong · Zhifang Sui
摘要
Large Language Models (LLMs) as judges across various scenarios such as assessing model responses is becoming an increasingly accepted paradigm. However, existing judgment approaches often rely on trained judgers using fixed preference data, which tend to overlook diverse user preferences and str...