Auditing Stance Asymmetry in Generative Explanations 事件

Auditing Stance Asymmetry in Generative Explanations arXiv:2605.27988v1 Announce Type: new Abstract: Bias evaluation for language models has made substantial progress on bounded comparisons, such as overt derogation, stereotype association, or label-sensitive differences under controlled substitutions. Open-ended explanations raise a different problem: they guide interpretation by assigning responsibility, legitimacy, context, and grievance. A model can avoid hostile language while making one s