Towards Piece-by-Piece Explanations for Chess Positions with SHAP

• URL: http://arxiv.org/abs/2510.25775v1
• Date: Sun, 26 Oct 2025 09:07:21 GMT
• Title: Towards Piece-by-Piece Explanations for Chess Positions with SHAP
• Authors: Francesco Spinnato,
• Abstract summary: We adapt SHAP (SHapley Additive exPlanations) to attribute a chess engines evaluation to specific pieces on the board.<n>By treating pieces as features and systematically ablating them, we compute additive, per-piece contributions that explain the engines output.<n>This method draws inspiration from classical chess pedagogy, where players assess positions by mentally removing pieces.
• Score: 0.20305676256390937
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use [52.394999779049606]
  Large Language Models (LLMs) are increasingly applied in high-stakes domains.<n>LLMs fail to compete against traditional algorithms.<n>We propose ToolPoker, a tool-integrated reasoning framework.
  arXiv  Detail & Related papers  (2026-01-31T05:45:25Z)
• Predicting Human Chess Moves: An AI Assisted Analysis of Chess Games Using Skill-group Specific n-gram Language Models [0.0]
  The framework employs n-gram language models to capture move patterns characteristic of specific player skill levels.<n>We trained separate models using data from the open-source chess platform Lichess.<n>The framework can classify skill levels with an accuracy of up to 31.7% when utilizing early game information.
  arXiv  Detail & Related papers  (2025-12-01T17:02:07Z)
• ChessQA: Evaluating Large Language Models for Chess Understanding [10.480398008794436]
  Chess provides an ideal testbed for evaluating the reasoning, modeling, and abstraction capabilities of large language models (LLMs)<n>We present ChessQA, a benchmark that assesses LLM chess understanding across five task categories.<n>We find persistent weaknesses across all five categories and provide results and error analyses by category.
  arXiv  Detail & Related papers  (2025-10-28T00:02:52Z)
• Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess [54.5355907369231]
  We investigate whether large language models (LLMs) can develop strategic reasoning capabilities through reinforcement learning (RL) in chess.<n>Our experiments show that our distillation-based dense rewards often outperform sparse binary rewards.<n>We provide SFT and RL ablations on chess reasoning training and find evidence that this limitation stems from a deficit in the pretrained models' internal understanding of chess.
  arXiv  Detail & Related papers  (2025-07-01T13:16:34Z)
• Explore the Reasoning Capability of LLMs in the Chess Testbed [45.12891789312405]
  We propose improving the reasoning capability of large language models in chess by integrating annotated strategy and tactic.<n>We finetune the LLaMA-3-8B model and compare it against state-of-the-art commercial language models in the task of selecting better chess moves.
  arXiv  Detail & Related papers  (2024-11-11T01:42:56Z)
• Aspect-based Sentiment Evaluation of Chess Moves (ASSESS): an NLP-based Method for Evaluating Chess Strategies from Textbooks [3.652509571098292]
  This study investigates the feasibility of using a modified sentiment analysis method as a means for evaluating chess moves based on text. By extracting insights from move-action phrases, our approach aims to provide a more fine-grained and contextually aware chess move'-based sentiment classification.
  arXiv  Detail & Related papers  (2024-05-10T14:23:43Z)
• Learning to Play Chess from Textbooks (LEAP): a Corpus for Evaluating Chess Moves based on Sentiment Analysis [4.314956204483074]
  This paper examines chess textbooks as a new knowledge source for enabling machines to learn how to play chess. We developed the LEAP corpus, a first and new heterogeneous dataset with structured (chess move notations and board states) and unstructured data. We performed empirical experiments that assess the performance of various transformer-based baseline models for sentiment analysis.
  arXiv  Detail & Related papers  (2023-10-31T08:26:02Z)
• Learning Chess Blindfolded: Evaluating Language Models on State Tracking [69.3794549747725]
  We consider the task of language modeling for the game of chess. Unlike natural language, chess notations describe a simple, constrained, and deterministic domain. We find that transformer language models can learn to track pieces and predict legal moves with high accuracy when trained solely on move sequences.
  arXiv  Detail & Related papers  (2021-02-26T01:16:23Z)
• Teach me to play, gamer! Imitative learning in computer games via linguistic description of complex phenomena and decision tree [55.41644538483948]
  We present a new machine learning model by imitation based on the linguistic description of complex phenomena. The method can be a good alternative to design and implement the behaviour of intelligent agents in video game development.
  arXiv  Detail & Related papers  (2021-01-06T21:14:10Z)
• Chess2vec: Learning Vector Representations for Chess [0.0]
  We generate and evaluate vector representations for chess pieces. We uncover the latent structure of chess pieces and moves, as well as predict chess moves from chess positions.
  arXiv  Detail & Related papers  (2020-11-02T14:50:48Z)
• Learning to Play Sequential Games versus Unknown Opponents [93.8672371143881]
  We consider a repeated sequential game between a learner, who plays first, and an opponent who responds to the chosen action. We propose a novel algorithm for the learner when playing against an adversarial sequence of opponents. Our results include algorithm's regret guarantees that depend on the regularity of the opponent's response.
  arXiv  Detail & Related papers  (2020-07-10T09:33:05Z)
• Playing Chess with Limited Look Ahead [0.0]
  We train a deep neural network to serve as a static evaluation function. We show that our static evaluation function has encoded some semblance of look ahead knowledge. We show that, despite strict restrictions on look ahead depth, our engine recommends moves of equal strength in roughly $83%$ of our sample positions.
  arXiv  Detail & Related papers  (2020-07-04T16:02:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.