Towards Piece-by-Piece Explanations for Chess Positions with SHAP
This addresses the need for interpretable AI in chess for players and researchers, though it is incremental as it applies an existing method to a new domain.
The paper tackled the problem of opaque evaluations from chess engines by adapting SHAP to attribute engine scores to individual pieces, enabling piece-by-piece explanations that are locally faithful and human-interpretable.
Contemporary chess engines offer precise yet opaque evaluations, typically expressed as centipawn scores. While effective for decision-making, these outputs obscure the underlying contributions of individual pieces or patterns. In this paper, we explore adapting SHAP (SHapley Additive exPlanations) to the domain of chess analysis, aiming to attribute a chess engines evaluation to specific pieces on the board. By treating pieces as features and systematically ablating them, we compute additive, per-piece contributions that explain the engines output in a locally faithful and human-interpretable manner. This method draws inspiration from classical chess pedagogy, where players assess positions by mentally removing pieces, and grounds it in modern explainable AI techniques. Our approach opens new possibilities for visualization, human training, and engine comparison. We release accompanying code and data to foster future research in interpretable chess AI.