mlsanityData to 7 Oct 2026

Communicating Chess Strategies in Natural Language

arXiv 2607.11486 ↗First posted 13 Jul 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Chess engines have long achieved superhuman playing strength. However, the underlying strategy behind their move suggestions is difficult for human players, even skilled ones, to comprehend. Motivated by this, we propose the task of chess strategy verbalization, which is to describe chess strategies in natural language. We design (i) a pipeline for verbalizing strategies and (ii) an evaluation framework for objective evaluation of generated strategy descriptions. Our experiments show that natural language is a promising and interpretable medium for communicating strategic information to both human and LLM players. We glean additional interesting insights, including (a) the importance of evaluating strategies beyond the main line, (b) the limitations of pure concept-based descriptions, and (c) the limitations of relying on LLMs rather than humans for evaluation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 47 references that are in the map. First posted on arXiv 13 Jul 2026.

Builds on

22 of 47 references.

References · 22

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  2. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  3. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  4. 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 265
  5. 2023Exploring Large Language Models for Communication Games: An Empirical Study on Werewolfcited by 238
  6. 2021Acquisition of Chess Knowledge in AlphaZerocited by 120
  7. 2020Aligning Superhuman AI with Human Behavior: Chess as a Model Systemcited by 78
  8. 2023ChessGPT: Bridging Policy Learning and Language Modelingcited by 73
  9. 2019Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attributioncited by 50
  10. 2021Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabicited by 37
  11. 2021On the Critical Role of Conventions in Adaptive Human-AI Collaborationcited by 26
  12. 2024Maia-2: A Unified Model for Human-AI Alignment in Chesscited by 24
10 more
  1. 2020Approximate exploitability: Learning a best response in large gamescited by 23
  2. 2025Complete Chess Games Enable LLM Become A Chess Mastercited by 16
  3. 2025DocAgent: A Multi-Agent System for Automated Code Documentation Generationcited by 16
  4. 2022Improving Chess Commentaries by Combining Language Models with Symbolic Reasoning Enginescited by 12
  5. 2025LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chesscited by 12
  6. 2025AI Self-preferencing in Algorithmic Hiring: Empirical Evidence and Insightscited by 10
  7. 2019Automated Chess Commentator Powered by Neural Chess Enginecited by 9
  8. 2023Hidden-Role Games: Equilibrium Concepts and Computationcited by 6
  9. 2025Towards Piece-by-Piece Explanations for Chess Positions with SHAPcited by 2
  10. 2026Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planningcited by 2

Built on by

Not cited yet.