arXiv cs.CL· Yuko Nakagi, Yuya Chiba, Yasue Kishino·· 12 小时前AI 评分18
对话中什么塑造了大语言模型与大脑的对齐？语言产出与理解的启示
What Shapes Brain Alignment of Large Language Models during Dialogue? Insights from Language Production and Comprehension
AI 导读
研究利用对话中采集的 fMRI 数据，考察大语言模型在语言产出与理解两种模式下跨层、跨脑区的脑对齐情况。结果显示产出与理解呈现不同的脑对齐模式，且与模型表示的内在维度（ID）在对应脑区强相关。语言与交际特征在不同加工模式、模型层和脑区中的贡献也各不相同。
正文 · 原文
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.
| Comments: | 33 pages |
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC) |
| Cite as: | arXiv:2610.22961 [cs.CL] |
| (or arXiv:2610.22961v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22961 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuko Nakagi [view email]
[v1]
Fri, 16 Oct 2026 05:34:33 UTC (44,234 KB)
来源：arXiv cs.CL · arxiv.org