counterfactual-testing

Tag

Cards List
#counterfactual-testing

Investigating Counterfactual Unfairness in LLMs towards Identities through Humor

arXiv cs.CL · 2026-04-22 Cached

Academic study exposes systemic counterfactual unfairness in LLMs: jokes from privileged speakers are refused 67% more often and rated as more malicious than identical jokes from marginalized speakers.

0 favorites 0 likes
← Back to home

Submit Feedback