This work proposes a method to rank feed-forward neurons at the final prompt token using a custom neuron selection dataset, and transfers the selected neuron identities to train hallucination classifiers on other factual question answering datasets.
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.
This work proposes a five-step diagnostic protocol covering feature correlation, bootstrap stability, sparse versus dense ranking disagreement, intervention baselines, and cross-dataset evaluation as a minimum standard for sparse-neuron localization claims, and investigates prior work using the proposed approach.
Huseyin Cavus, Sebin Sabu, J. Spear et al.· 0 citations
InnerExpert is introduced, the first method to leverage MoE-specific signals for per-token hallucination detection, and shows that InnerExpert outperforms existing methods across five datasets and two MoE architectures.
João Fonseca, Rodrigo Rodrigues, Paolo Romano· 0 citations
It is shown that epistemic uncertainty leaves a measurable trace within intermediate layers, where spikes in attention entropy are associated with reasoning breakdowns, and that attention dispersion is a promising complement to traditional hallucination detection methods.
This work introduces a two-stage keyword-perturbation method for hallucination detection and extends the same probabilistic framework to four hallucination regimes: knowledge deficit, wrong knowledge, context distraction, and unstable inference.
Xu-Han Tong, Hao-Yue Bai, Da-Wei Zhou et al.· 0 citations
A multi-signal detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo Dropout uncertainty quantification, and temperature-scaled calibration for response-level hallucination detection is presented.
Large language models are increasingly used for financial question answering, while they are prone to generating hallucinated content. In this research, we propose a multi-signal framework for hallucination detection and mitigation. Our framework combines six signals (entailment, semantic similarity, claim verification...
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
