6 papers
An Odd Estimator for Shapley Values
Fabian Fumagalli, Landon Butler, Justin Singh Kang +2
The Shapley value is a ubiquitous framework for attribution in machine learning, encompassing feature importance, data valuation, and causal inference. However, its exact computati…
Adaptive Sparse Möbius Transforms for Learning Polynomials
Yigit Efe Erginbas, Justin Singh Kang, Elizabeth Polito +1
We consider the problem of exactly learning an -sparse real-valued Boolean polynomial of degree of the form . This problem corresponds t…
A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior
Harry Mayne, Justin Singh Kang, Dewi Gould +3
LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process is poorly understood. Existing faithful…
ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
Landon Butler, Abhineet Agarwal, Justin Singh Kang +3
Large Language Models (LLMs) have achieved remarkable performance by capturing complex interactions between input features. To identify these interactions, most existing approaches…
SHAP zero Explains Biological Sequence Models with Near-zero Marginal Cost for Future Queries
Darin Tsui, Aryan Musharaf, Yigit Efe Erginbas +2
The growing adoption of machine learning models for biological sequences has intensified the need for interpretable predictions, with Shapley values emerging as a theoretically gro…
SPEX: Scaling Feature Interaction Explanations for LLMs
Justin Singh Kang, Landon Butler, Abhineet Agarwal +4
Large language models (LLMs) have revolutionized machine learning due to their ability to capture complex interactions between input features. Popular post-hoc explanation methods…