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

Shuqi Zhu, Yi Zhong, Ziyi Ye, Bangde Du, Yujia Zhou, Qingyao Ai, Yiqun Liu
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:168064-168079, 2026.

Abstract

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. The detailed code can be accessed openly through https://github.com/Promise-Z5Q2SQ/EEG-Hallucination.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-zhu26bh, title = {How do Humans Process {AI}-generated Hallucination Contents: a Neuroimaging Study}, author = {Zhu, Shuqi and Zhong, Yi and Ye, Ziyi and Du, Bangde and Zhou, Yujia and Ai, Qingyao and Liu, Yiqun}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {168064--168079}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/zhu26bh/zhu26bh.pdf}, url = {https://proceedings.mlr.press/v306/zhu26bh.html}, abstract = {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. The detailed code can be accessed openly through https://github.com/Promise-Z5Q2SQ/EEG-Hallucination.} }
Endnote
%0 Conference Paper %T How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study %A Shuqi Zhu %A Yi Zhong %A Ziyi Ye %A Bangde Du %A Yujia Zhou %A Qingyao Ai %A Yiqun Liu %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-zhu26bh %I PMLR %P 168064--168079 %U https://proceedings.mlr.press/v306/zhu26bh.html %V 306 %X 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. The detailed code can be accessed openly through https://github.com/Promise-Z5Q2SQ/EEG-Hallucination.
APA
Zhu, S., Zhong, Y., Ye, Z., Du, B., Zhou, Y., Ai, Q. & Liu, Y.. (2026). How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:168064-168079 Available from https://proceedings.mlr.press/v306/zhu26bh.html.

Related Material