arXiv 2610.03695 · cs.CL · 2026-10-02
Language Models that Play Chess and Explain Their Moves
Adithya Bhaskar, Jeffrey Cheng, Danqi Chen
机构待核实
在最新榜 #266 本站收录于 2026-10-26
一句话要点
Queen 是一个 40 亿参数的国际象棋语言模型,能边下棋边解释着法和计划,棋力达到一般特级大师水平;它通过交叉注意力把象棋编码器接到指令微调语言模型上,并用问答课程和迭代蒸馏训练。
Queen is a 4B chess-language model that explains its moves and plans while playing at typical Grandmaster level, connecting a chess encoder to an instruction-tuned LM via cross-attention and training with a QA curriculum and iterative distillation.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题:大语言模型
- Jeva: System One Models from First Principles ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions ▲273
- OmniEdu: Open Foundation Models for Learning and Teaching ▲240
- PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking ▲163
- MemT-1.0: Towards Memory-Native Evolution ▲143
同主题:推理
- LoopVL: Recurrent Visual Intelligence 2026-09-29 · ▲417
- LEV: Thinking Fast and Deep with Looped Decision Models 2026-10-14 · ▲337
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence 2026-09-28 · ▲224
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics 2026-09-28 · ▲205
数据说明
元数据来自 arXiv API(已核实);点赞来自 Hugging Face 每日论文;引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写,不转载摘要原文,请阅读原文。