4 papers
Joint Distribution-Informed Shapley Values for Sparse Counterfactual Explanations
Lei You, Yijun Bian, Lele Cao
Counterfactual explanations (CE) aim to reveal how small input changes flip a model's prediction, yet many methods modify more features than necessary, reducing clarity and actiona…
Be Wary of Your Time Series Preprocessing
Sofiane Ennadir, Tianze Wang, Oleg Smirnov +2
Normalization and scaling are fundamental preprocessing steps in time series modeling, yet their role in Transformer-based models remains underexplored from a theoretical perspecti…
Preventing the Collapse of Peer Review Requires Verification-First AI
Lei You, Lele Cao, Iryna Gurevych
This paper argues that AI-assisted peer review should be verification-first rather than review-mimicking. We propose truth-coupling, i.e. how tightly venue scores track latent scie…
Distributional Counterfactual Explanations With Optimal Transport
Lei You, Lele Cao, Mattias Nilsson +2
Counterfactual explanations (CE) are the de facto method for providing insights into black-box decision-making models by identifying alternative inputs that lead to different outco…