通过脑电图研究人类如何识别或被AI幻觉误导。
How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study
- 用脑电图记录27人看AI图像描述时的神经活动。
- 误判幻觉时大脑未激活标准事实验证路径。
- 发现语义整合与记忆检索等过程差异显著。
尽管AI生成的幻觉带来重大风险，但人类如何识别或被其误导的认知机制仍不明确。本文通过脑电图（EEG）记录27名参与者在判断多模态大语言模型（MLLM）生成图像描述正确性时的神经动态，基于平均事件相关电位（ERP）分析，揭示了在处理幻觉内容与非幻觉内容时，语义整合、推理加工、记忆检索及认知负荷等多种认知过程呈现出明显差异。值得注意的是，人类对幻觉内容的误判与正确判断所引发的神经反应存在显著区别，表明被误判的幻觉未能触发标准的神经认知事实验证通路。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。