大师混合：具有玩家路由的稀疏国际象棋语言模型
Mixture of Masters: Sparse Chess Language Models with Player Routing
AI总结：
本文提出Mixture-of-Masters模型，通过稀疏专家网络实现国际象棋生成的多样化与可控性，优于传统密集模型和GPT基线。
摘要：
现代国际象棋语言模型是基于数百万高水平玩家对局训练的密集转换器。然而，这些单一网络倾向于产生模式平均行为，风格边界模糊，罕见但有效的策略被压制。为对抗同质化，我们引入Mixture-of-Masters（MoM），首个具有小规模GPT专家的国际象棋混合专家模型，这些专家模拟世界级大师。对于每个移动，后验学习的门控网络根据游戏状态选择最合适的身份，使MoM能够动态切换风格，例如塔尔的进攻性或彼得罗西亚的防守性。在未见过的标准化游戏中评估MoM对抗Stockfish，其优于密集个体专家网络和流行的GPT基线，同时确保生成多样性、控制和可解释性。
英文摘要：
Modern chess language models are dense transformers trained on millions of games played by thousands of high-rated individuals. However, these monolithic networks tend to collapse into mode-averaged behavior, where stylistic boundaries are blurred, and rare but effective strategies are suppressed. To counteract homogenization, we introduce Mixture-of-Masters (MoM), the first chess mixture-of-experts model with small-sized GPT experts emulating world-class grandmasters. For each move, a post-hoc learnable gating network selects the most appropriate persona to channel depending on the game state, allowing MoM to switch its style dynamically, e.g., Tal's offensive vocation or Petrosian's defensive solidity. When evaluated against Stockfish on unseen standard games, MoM outperforms both dense individual expert networks and popular GPT baselines trained on aggregated data, while ensuring generation variety, control, and interpretability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
