Brain-guided language models for robust reasoning
English
Singapore, Singapore
Brain

数据描述

Brain-guided language models for robust reasoning

This dataset contains preprocessed fMRI brain responses from human participants solving deductive reasoning problems during neuroimaging, with per-subject response matrices of beta values extracted via GLMSingle from relevant brain regions (top 10% most responsive voxels within ROIs). It also includes generated reasoning datasets for deductive and propositional reasoning tasks, along with HCP fMRI data for cross-dataset validation. The data supports the development and evaluation of brain-guided language models for robust reasoning.

github.com
IP: 20.205.243.166
访问数据源
加载中...

相关论文

1

Beyond representational alignment with brain-guided language models for robust reasoning

Mingqing XiaoKai DuZhouchen Lin
Nature Machine Intelligence
2026
2026/8/3
00 p.1-15
The correspondence between large language models (LLMs) and the neural mechanisms underlying human higher-order cognition remains insufficiently characterized. Given that language and reasoning in the human brain appear dissociable, an open question is whether LLMs align with neural signals from rea...
Cognitive neuroscienceComputational scienceLearning algorithms
10.1038/S42256-026-01278-W
ISSN:2522-5839