Freddy Lecue

Cross Spline Net: A Simpler, More Interpretable and Unified Machine Learning Framework

Who Judges the Judge? LLM Jury-on-Demand: Building Trustworthy LLM Evaluation Systems

Inherently Interpretable Tree Ensemble Learning

Interpretable Graph Embeddings: Feature-Level Decomposition for Trustworthy Graph Neural Networks

The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples

Interpreting Language Reward Models via Contrastive Explanations

KnowHalu: Multi-Form Knowledge Enhanced Hallucination Detection

Language Models Can Help to Learn High-Performing Cost Functions for Recourse

Quantifying Prediction Consistency Under Fine-tuning Multiplicity in Tabular LLMs

Interpretable Table Question Answering via Plans of Atomic Table Transformations

Quantifying Prediction Consistency Under Model Multiplicity in Tabular LLMs

Everyone Deserves Recourse: Feasible Recourse Paths Using Data Augmentation