Chess作为语言模型状态跟踪的试验床
Chess as a Testbed for Language Model State Tracking
摘要：
Transformer语言模型在自然语言理解任务中取得了巨大的进步。然而，自然语言的复杂性使得确定这些模型跟踪文本背后的世界状态的准确性具有挑战性。出于这个问题，我们认为国际象棋游戏的语言建模的任务。与自然语言不同，国际象棋符号描述了一个简单的、受约束的、确定性的域。此外，我们观察到，国际象棋符号的适当选择允许直接探测世界状态，而不需要任何额外的探测相关的机器。我们发现：（a）有了足够的训练数据，Transformer语言模型就可以学习跟踪棋子，并在只对移动序列进行训练时高精度地预测合法移动。(b)对于小的训练集，在训练期间提供对板状态信息的访问可以产生显著的改进。(c)Transformer语言模型的成功取决于对整个游戏历史的访问，即“完全关注”。接近这种完全注意力会导致显著的性能下降。我们提出这个测试平台作为基准，为今后的工作的发展和分析的Transformer语言模型。
英文摘要：
Transformer language models have made tremendous strides in natural language understanding tasks. However, the complexity of natural language makes it challenging to ascertain how accurately these models are tracking the world state underlying the text. Motivated by this issue, we consider the task of language modeling for the game of chess. Unlike natural language, chess notations describe a simple, constrained, and deterministic domain. Moreover, we observe that the appropriate choice of chess notation allows for directly probing the world state, without requiring any additional probing-related machinery. We find that: (a) With enough training data, transformer language models can learn to track pieces and predict legal moves with high accuracy when trained solely on move sequences. (b) For small training sets providing access to board state information during training can yield significant improvements. (c) The success of transformer language models is dependent on access to the entire game history i.e. "full attention". Approximating this full attention results in a significant performance drop. We propose this testbed as a benchmark for future work on the development and analysis of transformer language models.
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。
