Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs

David Hartmann, Lena Pohlmann, Lelia Hanslik, Noah Gießing, Bettina Berendt, Pieter Delobelle


Abstract
Large Language Models (LLMs) exhibit systematic biases across demographic groups. Auditing is proposed as an accountability tool for black-box LLM applications, but suffers from resource-intensive query access. We conceptualise auditing as uncertainty estimation over a target fairness metric and introduce BAFA, the Bounded Active Fairness Auditor for query-efficient auditing of black-box LLMs. BAFA maintains a version space of surrogate models consistent with queried scores and computes uncertainty intervals for fairness metrics (e.g., 𝛥 AUC) via constrained empirical risk minimisation. Active query selection narrows these intervals to reduce estimation error. We evaluate BAFA on two standard fairness dataset case studies: CivilComments and Bias-in-Bios, comparing against stratified sampling, power sampling, and ablations. BAFA achieves target error thresholds with up to 40× fewer queries than stratified sampling (e.g., 144 vs 5,956 queries at 𝜀=0.02 for CivilComments) for tight thresholds, demonstrates substantially better performance over time, and shows lower variance across runs. These results suggest that active sampling can reduce resources needed for independent fairness auditing with LLMs, supporting continuous model evaluations.
Anthology ID:
2026.findings-acl.1681
Volume:
Findings of the Association for Computational Linguistics: ACL 2026
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Maria Liakata, Viviane P. Moreira, Jiajun Zhang, David Jurgens
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
33673–33698
Language:
URL:
https://aclanthology.org/2026.findings-acl.1681/
DOI:
Bibkey:
Cite (ACL):
David Hartmann, Lena Pohlmann, Lelia Hanslik, Noah Gießing, Bettina Berendt, and Pieter Delobelle. 2026. Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs. In Findings of the Association for Computational Linguistics: ACL 2026, pages 33673–33698, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs (Hartmann et al., Findings 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.findings-acl.1681.pdf
Checklist:
 2026.findings-acl.1681.checklist.pdf