Tsui-Wei Weng

Faithful and Stable Neuron Explanations for Trustworthy Mechanistic Interpretability

ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability

Evaluating Neuron Explanations: A Unified Framework with Sanity Checks

Graph Concept Bottleneck Models

Concept Bottleneck Large Language Models

Understanding Fixed Predictions via Confined Regions

A Principled Evaluation Framework for Neuron Explanations