Language Models (LMs) have achieved impressive performance on various linguistic tasks, but their relationship to human language processing in the brain remains unclear. This paper examines the gaps and overlaps between LMs and the brain at different levels of analysis, emphasizing the importance of looking beyond input-output behavior to examine and compare the internal processes of these systems. We discuss how insights from neuroscience, such as sparsity, modularity, internal states, and interactive learning, can inform the development of more biologically plausible language models. Furthermore, we explore the role of scaling laws in bridging the gap between LMs and human cognition, highlighting the need for efficiency constraints analogous to those in biological systems. By developing LMs that more closely mimic brain function, we aim to advance both artificial intelligence and our understanding of human cognition.

翻译：语言模型（LMs）在各种语言任务上取得了令人瞩目的性能，但其与大脑中人类语言处理的关系仍不明确。本文从不同分析层面审视了语言模型与大脑之间的差异与重叠，强调需要超越输入-输出行为，深入检视和比较这些系统的内部处理过程。我们探讨了神经科学中的见解——如稀疏性、模块化、内部状态和交互式学习——如何为开发更具生物学合理性的语言模型提供启示。此外，我们探索了缩放定律在弥合语言模型与人类认知之间鸿沟的作用，强调需要建立类似于生物系统的效率约束机制。通过开发更贴近大脑功能的语言模型，我们旨在同时推动人工智能的发展与人类认知理解的进步。