Low-Rank Tensor Encoding Models Decompose Natural Speech Comprehension Processes.

ABSTRACT: How does the brain process language over time? Research suggests that natural human language is processed hierarchically across brain regions over time. However, attempts to characterize this computation have thus far been limited to tightly controlled experimental settings that capture only a coarse picture of the brain dynamics underlying human natural language comprehension. The recent emergence of LLM encoding models promises a new avenue to discover and characterize rich semantic information in the brain, yet interpretable methods for linking information in LLMs to language processing over time are limited. In this work, we develop a low-rank tensor regression method to decompose LLM encoding models into interpretable components of semantics, time, and brain region activation, and app

SUBMITTER: Lewis L 

PROVIDER: S-EPMC12157526 | biostudies-literature | 2025 Jun

REPOSITORIES: biostudies-literature