collaborators

8 papers

cs.AI2026

Decomposition of Evidence, Contradiction, and Fragility in Perturbation Responses

Lei You

Perturbation methods explain model decisions by measuring prediction changes under altered inputs, but response magnitude tells us only how much a model reacts, not what that react…

cs.LG2026

Best-of-Evidence: Best-of-N Selection under Partial Verification

Cenwei Zhang, Teng Fang, Yuxia Wang +3

BoN improves model outputs by sampling several candidates and selecting one with a proxy score, but it assumes that complete candidates can be evaluated reliably. Many vision-langu…

cs.LG2026

DISCOVER: A Solver for Distributional Counterfactual Explanations

Yikai Gu, Lele Cao, Bo Zhao +2

Counterfactual explanations (CE) explain model decisions by identifying input modifications that lead to different predictions. Most existing methods operate at the instance level.…

cs.LG2026

From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows

Cenwei Zhang, Lin Zhu, Manxi Lin +1

Feature attributions often hide a critical modeling choice: they explain a prediction along a counterfactual path from a reference state to an input. Different baselines, interpola…

cs.LG2026

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…

cs.LG2026

xai-cola: A Python library for sparsifying counterfactual explanations

Lin Zhu, Lei You

Counterfactual explanation (CE) is an important domain within post-hoc explainability. However, the explanations generated by most CE generators are often highly redundant. This wo…