# Communicating Chess Strategies in Natural Language

arXiv: https://arxiv.org/abs/2607.11486 · HTML: https://mlsanity.com/paper/2607.11486/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 47 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Builds on (most cited first, 22 of 22)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning](https://mlsanity.com/paper/1711.00832/) (2017)
- [Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf](https://mlsanity.com/paper/2309.04658/) (2023)
- [Acquisition of Chess Knowledge in AlphaZero](https://mlsanity.com/paper/2111.09259/) (2021)
- [Aligning Superhuman AI with Human Behavior: Chess as a Model System](https://mlsanity.com/paper/2006.01855/) (2020)
- [ChessGPT: Bridging Policy Learning and Language Modeling](https://mlsanity.com/paper/2306.09200/) (2023)
- [Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution](https://mlsanity.com/paper/1912.12191/) (2019)
- [Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabi](https://mlsanity.com/paper/2107.07630/) (2021)
- [On the Critical Role of Conventions in Adaptive Human-AI Collaboration](https://mlsanity.com/paper/2104.02871/) (2021)
- [Maia-2: A Unified Model for Human-AI Alignment in Chess](https://mlsanity.com/paper/2409.20553/) (2024)
- [Approximate exploitability: Learning a best response in large games](https://mlsanity.com/paper/2004.09677/) (2020)
- [DocAgent: A Multi-Agent System for Automated Code Documentation Generation](https://mlsanity.com/paper/2504.08725/) (2025)
- [Complete Chess Games Enable LLM Become A Chess Master](https://mlsanity.com/paper/2501.17186/) (2025)
- [LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess](https://mlsanity.com/paper/2512.01992/) (2025)
- [Improving Chess Commentaries by Combining Language Models with Symbolic Reasoning Engines](https://mlsanity.com/paper/2212.08195/) (2022)
- [Automated Chess Commentator Powered by Neural Chess Engine](https://mlsanity.com/paper/1909.10413/) (2019)
- [AI Self-preferencing in Algorithmic Hiring: Empirical Evidence and Insights](https://mlsanity.com/paper/2509.00462/) (2025)
- [Hidden-Role Games: Equilibrium Concepts and Computation](https://mlsanity.com/paper/2308.16017/) (2023)
- [Towards Piece-by-Piece Explanations for Chess Positions with SHAP](https://mlsanity.com/paper/2510.25775/) (2025)
- [Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning](https://mlsanity.com/paper/2605.06840/) (2026)

## 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.