What Shapes Brain Alignment of Large Language Models during Dialogue? Insights from Language Production and Comprehension
Abstract
Brain alignment of large language models (LLMs) offers a way to investigate representational similarities between LLMs and the human brain during language processing. While previous studies have mainly focused on passive language comprehension, little is known about such alignment during dialogue, in which speakers engage in both language production and comprehension. In this study, using fMRI data collected during dialogue, we examine brain alignment during language production and comprehension across LLM layers and brain regions. We assess its association with the intrinsic dimension (ID) of LLM representations and the contributions of several interpretable linguistic and communicative features. Our results reveal distinct patterns of brain alignment between production and comprehension, as well as strong associations with ID in brain regions associated with each processing mode. Furthermore, we show that the contributions of linguistic and communicative features also vary across processing modes, LLM layers, and brain regions.
Related
- Deep-layer cortical tracking abruptly collapses in the absence of language comprehension
- A domain-general basal ganglia mechanism for inhibitory control during language comprehension
- Inside a Programmer's Brain: Dissociating Code and Language Comprehension Networks Using a Novel fMRI-ESM Protocol.
- Spoken language comprehension relies on context-dependent neural weighting of syntax and prosody
- Expertise modifies neural responses to causal inference during language comprehension
BibTeX
@misc{nakagi2026what,
title = {{What Shapes Brain Alignment of Large Language Models during Dialogue? Insights from Language Production and Comprehension}},
author = {Yuko Nakagi and Yuya Chiba and Yasue Kishino},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.22961},
eprint = {2610.22961},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.22961},
}
RIS
TY - UNPB
TI - What Shapes Brain Alignment of Large Language Models during Dialogue? Insights from Language Production and Comprehension
AU - Yuko Nakagi
AU - Yuya Chiba
AU - Yasue Kishino
PY - 2026
DA - 2026/10/16
PB - arXiv
DO - 10.48550/arxiv.2610.22961
UR - https://arxiv.org/abs/2610.22961
AB - Brain alignment of large language models (LLMs) offers a way to investigate representational similarities between LLMs and the human brain during language processing. While previous studies have mainly focused on passive language comprehension, little is known about such alignment during dialogue, in which speakers engage in both language production and comprehension. In this study, using fMRI data collected during dialogue, we examine brain alignment during language production and comprehension across LLM layers and brain regions. We assess its association with the intrinsic dimension (ID) of LLM representations and the contributions of several interpretable linguistic and communicative features. Our results reveal distinct patterns of brain alignment between production and comprehension, as well as strong associations with ID in brain regions associated with each processing mode. Furthermore, we show that the contributions of linguistic and communicative features also vary across processing modes, LLM layers, and brain regions.
ER -