{"ID":2848820,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.26025","arxiv_id":"2510.26025","title":"Exploring Human-AI Conceptual Alignment through the Prism of Chess","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.","short_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...","url_abs":"https://arxiv.org/abs/2510.26025","url_pdf":"https://arxiv.org/pdf/2510.26025v2","authors":"[\"Semyon Lomasov\",\"Judah Goldfeder\",\"Mehmet Hamza Erol\",\"Matthew So\",\"Yao Yan\",\"Addison Howard\",\"Nathan Kutz\",\"Ravid Shwartz Ziv\"]","published":"2025-10-29T23:40:40Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Transformer\",\"Large Language Model\"]","has_code":false,"code_links":[{"ID":607648,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2848820,"paper_url":"https://arxiv.org/abs/2510.26025","paper_title":"Exploring Human-AI Conceptual Alignment through the Prism of Chess","repo_url":"https://github.com/slomasov/ChessConceptsLLM","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}