Active Fairness Auditing
(ICML) Studies of query-based auditing algorithms that can estimate the demographic parity of ML models in a query-efficient manner.
- from
- Audit Algorithms
- added
- 2026-10-10
- likes
- 0
similar
-
The Fair Game: Auditing & debiasing AI algorithms overtime cambridge.org
(Cambridge Forum on AI: Law and Governance) Aims to simulate the evolution of ethical and legal frameworks in the society by creating an auditor which sends feedback to a debiasing algorithm deployed around an ML system.
-
Auditing Fairness by Betting arxiv.org
(Neurips) [Code] Sequential methods that allows for the continuous monitoring of incoming data from a black-box classifier or regressor.
-
The Fair Game: Auditing & debiasing AI algorithms over time cambridge.org
Jouarnal of Cambridge Forum on AI: Law and Governance
-
Auditing fairness under unawareness through counterfactual reasoning sciencedirect.com
(Information Processing & Management) Shows how to unveil whether a black-box model, complying with the regulations, is still biased or not.
-
CALM: Curiosity-Driven Auditing for Large Language Models arxiv.org
(AAAI) Auditing as a black-box optimization problem where the goal is to automatically uncover input-output pairs of the target LLMs that exhibit illegal, immoral, or unsafe behaviors.
-
AI Fairness 360 github.com
Fairness metrics for datasets and ML models, explanations, and algorithms to mitigate bias in datasets and models.
Audit Algorithms › Papers > 2022: “(ICML) Studies of query-based auditing algorithms that can estimate the demographic parity of ML models in a query-efficient manner.”