Language Models Show a "Women-Are-Wonderful" Effect in Blame Attribution That is Not Just Leniency

Anika Sharma, Snehalkumar 'Neil' S. Gaikwad, Snigdha Chaturvedi +1

This paper investigates the Women-Are-Wonderful (WaW) effect in language-model blame attribution: a favorable bias in which women receive more positive evaluations than men. Using…