标签
本文提出生成式验证（GenV），一种使用生成式奖励模型检测自动形式化中参考等价性失败的方法，解决神经符号系统的漏洞并提高验证准确性。
This paper analyzes reasoning shortcuts in neurosymbolic systems through symmetry and automorphism groups, reveals flaws in a prior framework, proves complexity-theoretic results, and empirically validates the corrected theory on benchmarks like CLE4EVR and rsbench.