AI Paper Atlas

Research map / Large language models / AI and society

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

ICML 2026 · Large language models › AI and society · approach: Human-centered trust and agency · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
hallucination words correctly recognized vs non-hallucination words: N100 amplitudehuman EEG response · EEG ERP, 27 participantsN100 amplitude: occipital F[1,26]=8.271, p<0.05Improved
correctly recognized hallucination words vs non-hallucination: N400 and P600human EEG response · EEG ERP, 27 participantsN400/P600 amplitude: central P600 F[1,26]=31.558, p<0.001Improved
misjudged hallucination words (HalluWrong) vs non-hallucination wordshuman EEG response · EEG ERP, 27 participantsERP amplitudeNo clear effect
misjudged vs correctly judged hallucination wordshuman EEG response · EEG ERP, 27 participantsERP amplitudeHurt
use EEG features to classify hallucinated vs non-hallucinated words and sentences (correctly recognized only)SVM, GBDT, attention model · HalluCorrect vs NoHallu, within-subjectAUC: word SVM 0.9393; sentence attention 0.9673Improved
classify EEG when humans failed to detect hallucination (HalluWrong vs NoHallu)SVM, GBDT, attention model · HalluWrong vs NoHalluAUC: SVM word within 0.5330No clear effect
cross-subject instead of within-subject split (ablation)word-level EEG classifiers · HalluCorrect vs NoHallu word-levelAUC: SVM 0.9393 -> 0.8631Hurt
sentence-level instead of word-level prediction (ablation)EEG classifiers · HalluCorrect vs NoHalluAUC: attention within 0.9113 -> 0.9673Improved
hallucination type (relation, entity, attribute) on ERP and accuracy (ablation)human participants · EEG studyrecognition accuracy: relation 90.88% vs attribute 86.18%No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy