Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference

NeurIPSSpotlight2025

Authors
Álvaro Parafita, Tomas Garriga, Axel Brando, Francisco J. Cazorla
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Among explainability techniques, SHAP stands out as one of the most popular, but often overlooks the causal structure of the problem…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

explainability causal

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive