How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Shuqi, Zhong, Yi, Ye, Ziyi, Du, Bangde, Zhou, Yujia, Ai, Qingyao, Liu, Yiqun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913161036169216
author Zhu, Shuqi
Zhong, Yi
Ye, Ziyi
Du, Bangde
Zhou, Yujia
Ai, Qingyao
Liu, Yiqun
author_facet Zhu, Shuqi
Zhong, Yi
Ye, Ziyi
Du, Bangde
Zhou, Yujia
Ai, Qingyao
Liu, Yiqun
contents While AI-generated hallucinations pose considerable risks, the underlying cognitive mechanisms by which humans can successfully recognize or be misled by these hallucinations remain unclear. To address this problem, this paper explores humans' neural dynamics to characterize how the brain processes hallucinated content. We record EEG signals from 27 participants while they are performing a verification task to judge the correctness of image descriptions generated by a multi-modal large language model (MLLM). Based on an averaged event-related potential (ERP) study, we reveal that multiple cognitive processes, e.g., semantic integration, inferential processing, memory retrieval, and cognitive load, exhibit distinct patterns when humans process hallucinated versus non-hallucinated content. Notably, neural responses to hallucinations that were misjudged versus correctly judged by human participants showed significant differences. This indicates that misjudged AI-generated hallucinations failed to trigger the standard neurocognitive fact verification pathway.
format Preprint
id arxiv_https___arxiv_org_abs_2605_16953
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study
Zhu, Shuqi
Zhong, Yi
Ye, Ziyi
Du, Bangde
Zhou, Yujia
Ai, Qingyao
Liu, Yiqun
Artificial Intelligence
Computation and Language
While AI-generated hallucinations pose considerable risks, the underlying cognitive mechanisms by which humans can successfully recognize or be misled by these hallucinations remain unclear. To address this problem, this paper explores humans' neural dynamics to characterize how the brain processes hallucinated content. We record EEG signals from 27 participants while they are performing a verification task to judge the correctness of image descriptions generated by a multi-modal large language model (MLLM). Based on an averaged event-related potential (ERP) study, we reveal that multiple cognitive processes, e.g., semantic integration, inferential processing, memory retrieval, and cognitive load, exhibit distinct patterns when humans process hallucinated versus non-hallucinated content. Notably, neural responses to hallucinations that were misjudged versus correctly judged by human participants showed significant differences. This indicates that misjudged AI-generated hallucinations failed to trigger the standard neurocognitive fact verification pathway.
title How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2605.16953