一作ACL 2026Poster· Natural Language Processing
C 2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences
Akira Kawabata · Saku Sugawara
摘要
Rubric-augmented verification guides reward models with explicit evaluation criteria, yielding more reliable judgments than single-model verification.However, most existing methods require costly rubric annotations, limiting scalability.Moreover, we find that rubric generation is vulnerable to a...