Happy to be at the #XAI World Conference 2025 in Istanbul. I will be presenting our work 📄"EvalxNLP: A Framework for Benchmarking Post-Hoc Explainability Methods on NLP Models" in the poster sessions tomorrow, so feel free to pass by to talk more about the usability of explainability methods!
In this paper, we show that widely used post-hoc feature attribution methods exhibit significant gender disparity with respect to their faithfulness, robustness, and complexity.
This work was done with Ege Erdogan, @nfel.bsky.social , and Gjergji Kasneci.
Very happy to be at #FAccT2025 in Athens, where I presented our work "Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods"
📄Paper: dl.acm.org/doi/10.1145/...
At #FAccT2025? Let's connect if you're interested in improving the usability of explainability methods!
