Manuela Veloso

7

Papers

14

Total Citations

Papers (7)

FairWASP: Fast and Optimal Fair Wasserstein Pre-processing

Interpreting Language Reward Models via Contrastive Explanations

To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models

Auditing and Enforcing Conditional Fairness via Optimal Transport

Accelerating Cutting-Plane Algorithms via Reinforcement Learning Surrogates

Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions

Counterfactual Metarules for Local and Global Recourse