Prof. LI Ping, Department of Chinese and Bilingual Studies

Model-Brain Alignment for Discourse Comprehension. Society for the Neurobiology of Language (SNL 2024) 16th Annual Meeting. Society for the Neurobiology of Language, Brisbane, Australia, 24-26 October 2024.

Abstract
Reading comprehension remains the main medium for students to gain scientific knowledge despite pervasive use of digital platforms. In this talk, I describe the “model-brain alignment” approach that leverages Large Language Models (LLMs) to study naturalistic reading comprehension in both native (L1) and non-native (L2) languages. By training LLM-based encoding models on brain responses to text reading, we can evaluate (a) what computational properties in the model are important to reflect human brain mechanisms in language comprehension, and (b) what model variations best reflect human individual differences during reading comprehension. Our findings show that first, to capture the differences in word-level processing vs. high-level discourse integration, current LLM-based models need to incorporate sentence prediction mechanisms on top of word prediction, and second, variations in model-brain alignment allow us to predict L1 and L2 readers’ sensitivity to text properties, cognitive demand characteristics, and ultimately their reading performance.