NeuroActiSep: Detecting Factual Hallucinations from Feed-Forward Neurons in a Single Pass

2026-09-13

AI Summary

本文提出一种通过单次检测前馈神经元来识别大语言模型中事实性幻觉的方法，使用定制数据集选择并转移相关神经元以训练分类器。

Abstract

Hallucination in large language models reduces their reliability and slows adoption. Various white-box studies have used internal representations to detect patterns of truthfulness and factuality. A less-studied approach is to identify feed-forward neurons correlated with hallucination. We propose a method to rank feed-forward neurons at the final prompt token using a custom neuron selection dataset. We transfer the selected neuron identities to train hallucination classifiers on other factual question answering datasets. Our work provides empirical evidence that probes trained using the features from the selected neurons perform on par with probes trained on internal states. We also analyze the distribution of selected neurons and the effect of layer depth on detection performance.

Problem

• Hallucination
• Large Language Models
• Factuality

Innovation

• feed-forward neurons
• hallucination detection
• single pass
• neuron ranking
• factual question answering