大模型推理能力

BiasCause: Evaluate Socially Biased Causal Reasoning of Large Language Models

BiasCause: 评估大型语言模型的社会偏见因果推理

Tian Xie, Tongxin Yin, Vaishakh Keshava, Xueru Zhang, Siddhartha Reddy Jonnalagadda

机构 * Google（谷歌） ； The Ohio State University（俄亥俄州立大学） 纠错

专题命中 代码与定理证明 ：reasoning(title,abstract)；分类 cs.CL

AI总结 本文提出BiasCause框架，评估LLMs在回答社会偏见问题时的因果推理，揭示其偏见产生机制及去偏策略。

Comments This work has been done when the first author is at Google. The first author is a student at the Ohio State University