Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs
BAFA, the Bounded Active Fairness Auditor is introduced, the Bounded Active Fairness Auditor for query-efficient auditing of black-box LLMs, suggesting that active sampling can reduce resources needed for independent fairness auditing with LLMs, supporting continuous model evaluations.
David Hartmann, Lena Pohlmann, Lelia Hanslik et al.
· Annual Meeting of the Associ... · 7 citations