arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.07582cs.LGcs.AI
收藏

简单Transformer中的线性潜在世界模型:基于Othello-GPT的案例研究

Linear Latent World Models in Simple Transformers: A Case Study on Othello-GPT

Harvard University(哈佛大学)

Dean S. Hazineh, Zechen Zhang, Jeffery Chiu

AI总结:

本文通过案例研究Othello-GPT,发现其内部形成了对棋的线性世界表示,该表示在因果上引导决策过程,并受层深度和模型复杂性影响。

摘要:

基础模型在决策和逻辑推理方面展现出显著能力。然而,关于它们是对世界的真正理解还是仅仅进行随机模仿,持续存在争议。本文细致地考察了一个为黑白棋训练的简单Transformer,扩展先前研究以增强对Othello-GPT涌现世界模型的理解。研究揭示,Othello-GPT包含对棋的线性表示,这一因素在因果上引导其决策过程。本文进一步阐明了线性世界表示与因果决策之间的相互作用,及其对层深度和模型复杂性的依赖。我们已公开代码。

英文摘要:

Foundation models exhibit significant capabilities in decision-making and logical deductions. Nonetheless, a continuing discourse persists regarding their genuine understanding of the world as opposed to mere stochastic mimicry. This paper meticulously examines a simple transformer trained for Othello, extending prior research to enhance comprehension of the emergent world model of Othello-GPT. The investigation reveals that Othello-GPT encapsulates a linear representation of opposing pieces, a factor that causally steers its decision-making process. This paper further elucidates the interplay between the linear world representation and causal decision-making, and their dependence on layer depth and model complexity. We have made the code public.

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。

↑