1
CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging
基于标准中心的推理对齐新范式，显著提升大模型代码偏好判断的准确性与可解释性。
arXiv:2605.19665v1 Announce Type: cross Abstract: Pairwise human preference prediction is central to evaluating code-generation systems, where quality…