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

원문 초록

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. In this empirical study, we propose a method to rank feed-forward neurons at the final prompt token and use it to investigate the feasibility of utilizing them for hallucination detection in the first forward pass. Using a neuron selection dataset built from CounterFact for identifying neurons correlated with hallucination, 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 sparse sets of selected neurons perform on par with probes trained on internal representations. We also analyze the distribution of selected neurons and the effects of layer depth and neuron budget on detection performance. Our results show that randomly drawn neuron sets are also competitive at larger budgets, suggesting that signals correlated with hallucination are distributed across many neurons, while selection can help in extremely sparse sets.