Language models have been shown to be very effective in predicting brain recordings of subjects experiencing complex language stimuli. For a deeper understanding of this alignment, it is important to understand the correspondence between the detailed processing of linguistic information by the human brain versus language models. We investigate this correspondence via a direct approach, in which we eliminate information related to specific linguistic properties in the language model representations and observe how this intervention affects the alignment with fMRI brain recordings obtained while participants listened to a story. We investigate a range of linguistic properties (surface, syntactic, and semantic) and find that the elimination of each one results in a significant decrease in brain alignment. Specifically, we find that syntactic properties (i.e. Top Constituents and Tree Depth) have the largest effect on the trend of brain alignment across model layers. These findings provide clear evidence for the role of specific linguistic information in the alignment between brain and language models, and open new avenues for mapping the joint information processing in both systems. We make the code publicly available [https://github.com/subbareddy248/linguistic-properties-brain-alignment].

翻译：语言模型已被证明在预测受试者在处理复杂语言刺激时的大脑记录方面非常有效。为深入理解这种对齐关系，关键是要弄清人脑与语言模型在语言信息精细处理上的对应关系。我们通过一种直接方法研究了这种对应关系，即从语言模型表征中剔除与特定语言属性相关的信息，并观察这种干预如何影响与参与者听故事时记录的fMRI脑信号的比对。我们考察了多种语言属性（表层、句法和语义），发现剔除每一种属性都会导致大脑对齐程度的显著下降。具体而言，句法属性（即顶层构成成分和树深度）对跨模型层的大脑对齐趋势影响最大。这些发现为特定语言信息在大脑与语言模型对齐中的作用提供了明确证据，并为绘制这两个系统中的联合信息处理图景开辟了新途径。我们已将代码公开：[https://github.com/subbareddy248/linguistic-properties-brain-alignment]。