Exploring Human-AI Conceptual Alignment through the Prism of Chess

• URL: http://arxiv.org/abs/2510.26025v2
• Date: Tue, 04 Nov 2025 03:29:09 GMT
• Title: Exploring Human-AI Conceptual Alignment through the Prism of Chess
• Abstract summary: Do AI systems truly understand human concepts or merely mimic surface patterns?<n>We investigate this through chess, where human creativity meets precise strategic concepts.<n>Our analysis exposes a fundamental tension in current architectures: the representations that win games diverge from those that align with human thinking.
• Score: 9.971673324195761
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Do AI systems truly understand human concepts or merely mimic surface patterns? We investigate this through chess, where human creativity meets precise strategic concepts. Analyzing a 270M-parameter transformer that achieves grandmaster-level play, we uncover a striking paradox: while early layers encode human concepts like center control and knight outposts with up to 85\% accuracy, deeper layers, despite driving superior performance, drift toward alien representations, dropping to 50-65\% accuracy. To test conceptual robustness beyond memorization, we introduce the first Chess960 dataset: 240 expert-annotated positions across 6 strategic concepts. When opening theory is eliminated through randomized starting positions, concept recognition drops 10-20\% across all methods, revealing the model's reliance on memorized patterns rather than abstract understanding. Our layer-wise analysis exposes a fundamental tension in current architectures: the representations that win games diverge from those that align with human thinking. These findings suggest that as AI systems optimize for performance, they develop increasingly alien intelligence, a critical challenge for creative AI applications requiring genuine human-AI collaboration. Dataset and code are available at: https://github.com/slomasov/ChessConceptsLLM.

Related papers

• AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games [63.29377274531968]
  We introduce the AI GameStore, a scalable and open-ended platform to synthesize new representative human games.<n>We generate 100 such games based on the top charts of Apple App Store and Steam, and evaluate seven frontier vision-language models (VLMs) on short episodes of play.<n>The best models achieved less than 10% of the human average score on the majority of the games, and especially struggled with games that challenge world-model learning, memory and planning.
  arXiv  Detail & Related papers  (2026-02-19T18:17:25Z)
• A Definition of AGI [208.25193480759026]
  The lack of a concrete definition for Artificial General Intelligence obscures the gap between today's specialized AI and human-level cognition.<n>This paper introduces a quantifiable framework to address this, defining AGI as matching the cognitive versatility and proficiency of a well-educated adult.
  arXiv  Detail & Related papers  (2025-10-21T01:28:35Z)
• People use fast, flat goal-directed simulation to reason about novel problems [68.55490343866545]
  We show that people are systematic and adaptively rational in how they play a game for the first time.<n>We explain these capacities via a computational cognitive model that we call the "Intuitive Gamer"<n>Our work offers new insights into how people rapidly evaluate, act, and make suggestions when encountering novel problems.
  arXiv  Detail & Related papers  (2025-10-13T15:12:08Z)
• A Behavior-Based Knowledge Representation Improves Prediction of Players' Moves in Chess by 25% [2.232417329532027]
  This paper proposes a novel approach combining expert knowledge with machine learning techniques to predict human players' next moves.<n>By applying feature engineering grounded in domain expertise, we seek to uncover the patterns in the moves of intermediate-level chess players.<n>Our methodology offers a promising framework for anticipating human behavior, advancing both the fields of AI and human-computer interaction.
  arXiv  Detail & Related papers  (2025-04-07T18:49:00Z)
• Maia-2: A Unified Model for Human-AI Alignment in Chess [10.577896749797485]
  We propose a unified modeling approach for human-AI alignment in chess. We introduce a skill-aware attention mechanism to dynamically integrate players' strengths with encoded chess positions. Our results pave the way for deeper insights into human decision-making and AI-guided teaching tools.
  arXiv  Detail & Related papers  (2024-09-30T17:54:23Z)
• Visual Agents as Fast and Slow Thinkers [88.1404921693082]
  We introduce FaST, which incorporates the Fast and Slow Thinking mechanism into visual agents.<n>FaST employs a switch adapter to dynamically select between System 1/2 modes.<n>It tackles uncertain and unseen objects by adjusting model confidence and integrating new contextual data.
  arXiv  Detail & Related papers  (2024-08-16T17:44:02Z)
• Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero [10.569213003371654]
  We show how to extract new chess concepts from AlphaZero, an AI system that mastered the game of chess via self-play without human supervision. In a human study, we show that these concepts are learnable by top human experts, as four top chess grandmasters show improvements in solving the presented concept prototype positions. This marks an important first milestone in advancing the frontier of human knowledge by leveraging AI.
  arXiv  Detail & Related papers  (2023-10-25T06:49:26Z)
• The MineRL BASALT Competition on Learning from Human Feedback [58.17897225617566]
  The MineRL BASALT competition aims to spur forward research on this important class of techniques. We design a suite of four tasks in Minecraft for which we expect it will be hard to write down hardcoded reward functions. We provide a dataset of human demonstrations on each of the four tasks, as well as an imitation learning baseline.
  arXiv  Detail & Related papers  (2021-07-05T12:18:17Z)
• Aligning Superhuman AI with Human Behavior: Chess as a Model System [5.236087378443016]
  We develop Maia, a customized version of Alpha-Zero trained on human chess games, that predicts human moves at a much higher accuracy than existing engines. For a dual task of predicting whether a human will make a large mistake on the next move, we develop a deep neural network that significantly outperforms competitive baselines.
  arXiv  Detail & Related papers  (2020-06-02T18:12:52Z)
• Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense [142.53911271465344]
  We argue that the next generation of AI must embrace "dark" humanlike common sense for solving novel tasks. We identify functionality, physics, intent, causality, and utility (FPICU) as the five core domains of cognitive AI with humanlike common sense.
  arXiv  Detail & Related papers  (2020-04-20T04:07:28Z)

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.