• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI
    Announcement

    QUEEN debuts as a chess model that explains its moves

    The authors estimate playing strength near a grandmaster’s Lichess rating, while acknowledging errors in explanations.

    DC
    CL
    AB
    4 Sources, ,

    TLDR

    Jeffrey Cheng introduced QUEEN, a 4-billion-parameter chess model that explains its moves. Its authors estimate a 2,697 rating from 32 engine games calibrated to Lichess, close to their grandmaster comparison. Explanations can still contain mistaken chess concepts. Code is public; fuller documentation is forthcoming and GPU setup validation continues.

    Combined views

    8.9K

    4 Sources, first seen 2h ago

    Combined views

    8.9K

    4 Sources, first seen 2h ago

    226 likes

    Useful links

    arXiv.org

    Language Models that Play Chess and Explain Their Moves
    2h ago
    first seen 2h ago
    226 likes
    5 comments
    155 saves
    31 reposts
    5 comments
    155 saves
    31 reposts

    Jeffrey Cheng introduced QUEEN on Oct. 5 as a chess model that chooses moves and explains them in natural language. His announcement describes a 4-billion-parameter model approaching a typical grandmaster’s playing strength.

    Featured Source

    What the benchmark measures

    The authors’ preprint combines a Leela Chess Zero encoder with SmolLM3-3B, then trains on explanations of candidate moves and their continuations. Seven rounds of search distillation raised its estimated rating from 1,782 to 2,697.

    That estimate comes from 32 games against eight engines, calibrated to the Lichess Elo scale. The paper compares it with a median grandmaster’s Lichess blitz rating of 2,730. It is not a formal grandmaster title or FIDE rating.

    Explanations remain fallible. A language-model judge scored QUEEN’s conceptual coherence below the tested frontier models, and the authors warn that mistaken chess motifs can propagate through training.

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Useful Links

    arXiv.org

    Language Models that Play Chess and Explain Their Moves
    Today's Rank

    #8

    Today's Rank

    #8

    Code and documentation

    The public repository contains training, data-generation and evaluation code, and links to model downloads. Its README promises fuller documentation and a cleaned code release. It also cautions that the combined GPU inference setup is still being validated.

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    6 Sources

    arxiv.orgLanguage Models that Play Chess and Explain Their Moves
    GitHubGitHub - queen-project/queen: Codebase for "Language Models that Play Chess and Explain their Moves"
    @AdithyaNLPThe most profound paper of my PhD so far. We truly did something special to make LMs play/explain chess, needing both architectural & algorithmic innovation (natural-language analogue of the Alphazero algorithm) + applicable to many other domains. Please read on and share! 1/102h
    @ChengleiSiRT @AdithyaNLP: The most profound paper of my PhD so far. We truly did something special to make LMs play/explain chess, needing both archi…2h
    @jeff_cheng_77‼️Have you ever used a chess engine and wished it could explain its moves and evaluations?‼️ Introducing QUEEN, a 4B-parameter chess-language model that plays at the level approaching a typical Grandmaster and explains its moves in natural language.2h
    @danqi_chenRT @jeff_cheng_77: ‼️Have you ever used a chess engine and wished it could explain its moves and evaluations?‼️ Introducing QUEEN, a 4B-pa…1h

    Useful Links

    arXiv.org

    Language Models that Play Chess and Explain Their Moves

    6 Sources

    arxiv.orgLanguage Models that Play Chess and Explain Their Moves
    GitHubGitHub - queen-project/queen: Codebase for "Language Models that Play Chess and Explain their Moves"
    @AdithyaNLPThe most profound paper of my PhD so far. We truly did something special to make LMs play/explain chess, needing both architectural & algorithmic innovation (natural-language analogue of the Alphazero algorithm) + applicable to many other domains. Please read on and share! 1/102h
    @ChengleiSiRT @AdithyaNLP: The most profound paper of my PhD so far. We truly did something special to make LMs play/explain chess, needing both archi…2h
    @jeff_cheng_77‼️Have you ever used a chess engine and wished it could explain its moves and evaluations?‼️ Introducing QUEEN, a 4B-parameter chess-language model that plays at the level approaching a typical Grandmaster and explains its moves in natural language.2h
    @danqi_chenRT @jeff_cheng_77: ‼️Have you ever used a chess engine and wished it could explain its moves and evaluations?‼️ Introducing QUEEN, a 4B-pa…1h