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

TL;DR

This neuroimaging study investigates how the human brain processes AI-generated hallucinations, revealing distinct neural patterns and cognitive mechanisms involved in recognizing or being misled by hallucinated content.

Contribution

The paper provides novel insights into the neural dynamics and cognitive processes underlying human interaction with AI hallucinations, using EEG data during a verification task.

Findings

Neural responses differ between hallucinated and non-hallucinated content.

Misjudged hallucinations do not activate standard neurocognitive verification pathways.

Distinct ERP patterns are associated with different cognitive processes during hallucination processing.

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.