Update. Without knowing author names, #ChatGPT rated male first-authored articles higher in quality than female first-au...

Update. Without knowing author names, #ChatGPT rated male first-authored articles higher in quality than female first-authored papers. The results differed by discipline. But in some fields, the male-preference disparity was even larger than the same disparity in #REF ratings.https://arxiv.org/abs/2608.09552"Gender differences were not evident for solo research in the social sciences, arts and humanities…The male-favouring pattern for first-authored research was not explained by gender differences in writing styles, at least as reflected in abstract complexity…Average ChatGPT scores may differ by first-author gender indirectly through other factors, such as field, topic, method, journal context or authorship structure. Thus, this is an additional reason to be cautious with AI-based research evaluation."#AI #Gender #GenderBias