Exploring Next
Exploring Next — Ep 208 w/ Justy & Cody — H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs Cheng Gao, Huimin Chen, Chaojun Xiao, Zhiyi Chen, Zhiyuan Liu, Maosong Sun Tsinghua University {gaoc24}@mails.tsinghua.edu.cn , {huimchen,xcj,liuzy}@tsinghua.edu.cn Abstract Large language models (LLMs) frequently generate hallucinations – plausible but factually incorrect outputs – undermining their reliability. While prior work has examined hallucinations from macroscopic perspectives such as training data and objectives, the underlying neuron-level mechanisms remain largely unexplored.