Joint processing of linguistic properties in brains and language models (2212.08094v2)

Abstract: LLMs 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 LLMs. We investigate this correspondence via a direct approach, in which we eliminate information related to specific linguistic properties in the LLM 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 LLMs, 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].