Enter a brief description of your changes
(Required)
Minor changes are by default collapsed in the page history.
No changes
The page does not exist yet.
Failed to load changes
Version by on
Leave Collaboration
Are you sure you want to leave the realtime collaboration and continue editing alone? The changes you save while editing alone will lead to merge conflicts with the changes auto-saved by the realtime editing session.
Unmasking the Shadows: Leveraging Symbolic Knowledge Extraction to Discover Biases and Unfairness in Opaque Predictive Models
Proceedings of the 2nd Workshop on Fairness and Bias in AI co-located with 27th European Conference on Artificial Intelligence (ECAI 2024)
CEUR Workshop Proceedings 3808
Sun SITE Central Europe, RWTH Aachen University
October 2024
This work explores the efficacy of symbolic knowledge-extraction (SKE) techniques in identifying biases and unfairness within opaque predictive models. Logic rules extracted from black-box predictors make it possible to verify if decisions are influenced by protected or sensitive features. In particular, the identification of biased or unfair decisions can be achieved through the evaluation of if-then rules, detecting the inclusion of protected and/or sensitive information in the rules’ precondition. The effectiveness of SKE in this regard is demonstrated here by conducting various simulations on a well-known data set for loan grant prediction. Our findings highlight the potential of SKE as a valuable tool to reveal biases and discrimination in opaque predictions, ultimately contributing to the pursuit of fair and transparent decision-making systems.
keywordsFairness in AI, Bias in AI, Explainable artificial intelligence, XAI, Symbolic knowledge extraction, PSyKE
AEQUITAS — Assessment and Engineering of eQuitable, Unbiased, Impartial and Trustworthy Ai Systems (01/11/2022–31/10/2025)