Shahaf Bassan

Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees

Provably Explaining Neural Additive Models

Unifying Formal Explanations: A Complexity-Theoretic Perspective

FAME: Formal Abstract Minimal Explanation for Neural Networks

How Should We Evaluate LLM Reasoning Quality For Fact Verification?

Additive Models Explained: A Computational Complexity Approach

SHAP Meets Tensor Networks: Provably Tractable Explanations with Parallelism

Abstracting and Refining Provably Sufficient Explanations of Neural Network Predictions

Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations

Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasons

On the (un) interpretability of Ensembles: A Computational Analysis

What makes an Ensemble (Un) Interpretable?