H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
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. In this paper, we conduct a systematic investigation into hallucination-associated neurons (H-Neurons) in LLMs from three perspectives: identification, behavioral impact, and origins. Regarding their identification, we demonstrate that a remarkably sparse subset of neurons (less than $0.1\%$ of total neurons) can reliably predict hallucination occurrences, with strong generalization across diverse scenarios. In terms of behavioral impact, controlled interventions reveal that these neurons are causally linked to over-compliance behaviors. Concerning their origins, we trace these neurons back to the pre-trained base models and find that these neurons remain predictive for hallucination detection, indicating they emerge during pre-training. Our findings bridge macroscopic behavioral patterns with microscopic neural mechanisms, offering insights for developing more reliable LLMs.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Readable but Not Controllable: Neuron-Level Evidence for Medical LLM Hallucination
Hallucination remains one of the central obstacles to deploying medical LLMs. Yet, even when hallucination can be detected, it is still unclear whether the internal representations associated with it can be used for cont…
Finding Culture-Sensitive Neurons in Vision-Language Models
Despite their impressive performance, vision-language models (VLMs) still struggle on culturally situated inputs. To understand how VLMs process culturally grounded information, we study the presence of culture-sensitive…
Visual Question AnsweringMIHBench: Benchmarking and Mitigating Multi-Image Hallucinations in Multimodal Large Language Models
Despite growing interest in hallucination in Multimodal Large Language Models, existing studies primarily focus on single-image settings, leaving hallucination in multi-image scenarios largely unexplored. To address this…
Style-Specific Neurons for Steering LLMs in Text Style Transfer
Text style transfer (TST) aims to modify the style of a text without altering its original meaning. Large language models (LLMs) demonstrate superior performance across multiple tasks, including TST. However, in zero-sho…
DiversityStyle TransferText Style TransferTowards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering
LVLMs achieve remarkable multimodal understanding and generation but remain susceptible to hallucinations. Existing mitigation methods predominantly focus on output-level adjustments, leaving the internal mechanisms that…
Visual Grounding