2 papers
cs.CL2026
C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences
Akira Kawabata, Saku Sugawara
Rubric-augmented verification guides reward models with explicit evaluation criteria, yielding more reliable judgments than single-model verification. However, most existing method…
cs.CL2024
Rationale-Aware Answer Verification by Pairwise Self-Evaluation
Akira Kawabata, Saku Sugawara
Answer verification identifies correct solutions among candidates generated by large language models (LLMs). Current approaches typically train verifier models by labeling solution…