Rohan Paul· @rohanpaul_ai · X·· 2 小时前AI 评分41
AI 导读
– https://arxiv.org/abs/2610.30349 标题：“一致性不等于有效性：自奖励的道德论证让语言模型变得果断却易被左右”
正文
– https://arxiv.org/abs/2610.30349
Title: "Consistency Is Not Validity: Self-Rewarded Moral Argumentation Makes Language Models Decisive but Pliable"
来源：Rohan Paul · x.com