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

• URL: http://arxiv.org/abs/2609.14448v1
• Date: Sun, 13 Sep 2026 11:42:40 GMT
• Title: NeuroActiSep: Detecting Factual Hallucinations from Feed-Forward Neurons in a Single Pass
• Abstract summary: A less-studied approach is to identify feed-forward neurons correlated with hallucination.<n>We propose a method to rank feed-forward neurons at the final prompt token using a custom neuron selection dataset.<n>Our work provides empirical evidence that probes trained using the features from the selected neurons perform on par with probes trained on internal states.
• Score: 0.17205106391379021
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Towards Interpretable Hallucination Analysis and Mitigation in LVLMs via Contrastive Neuron Steering [60.23509717784518]
  Existing mitigation methods predominantly focus on output-level adjustments, leaving internal mechanisms that give rise to hallucinations largely unexplored.<n>We propose Contrastive Neuron Steering ( CNS), which identifies image-specific neurons via contrastive analysis between clean and noisy inputs.<n> CNS selectively amplifies informative neurons while suppressing perturbation-induced activations, producing more robust and semantically grounded visual representations.
  arXiv  Detail & Related papers  (2026-01-31T09:21:04Z)
• H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs [56.31565301428888]
  We identify hallucination-associated neurons (H-Neurons) in large language models (LLMs)<n>In terms of identification, we demonstrate that a remarkably sparse subset of neurons can reliably predict hallucination occurrences.<n>In terms of behavioral impact, controlled interventions reveal that these neurons are causally linked to over-compliance behaviors.
  arXiv  Detail & Related papers  (2025-12-01T15:32:14Z)
• Know Thyself by Knowing Others: Learning Neuron Identity from Population Context [9.798773806523114]
  We present the first systematic scaling analysis for neuron-level representation learning.<n>We show that increasing the number of animals used during pretraining consistently improves downstream performance.<n>Results highlight how large, diverse neural datasets enable models to recover information about neuron identity that generalize across animals.
  arXiv  Detail & Related papers  (2025-12-01T02:28:04Z)
• Deciphering Functions of Neurons in Vision-Language Models [38.978287253624565]
  This study aims to delve into the internals of vision-language models (VLMs) to interpret the functions of individual neurons.<n>We observe the activations of neurons with respects to the input visual tokens and text tokens, and reveal some interesting findings.<n>We build a framework that automates the explanation of neurons with the assistant of GPT-4o.<n>For visual neurons, we propose an activation simulator to assess the reliability of the explanations for visual neurons.
  arXiv  Detail & Related papers  (2025-02-10T10:00:06Z)
• Neuron Empirical Gradient: Discovering and Quantifying Neurons Global Linear Controllability [14.693407823048478]
  We show that the neuron empirical gradient (NEG) captures how changes in activations affect predictions.<n>We also show that NEG effectively captures language skills across diverse prompts through skill neuron probing.<n>Further analysis highlights the key properties of NEG-based skill representation: efficiency, robustness, flexibility, and interdependency.
  arXiv  Detail & Related papers  (2024-12-24T00:01:24Z)
• WaLiN-GUI: a graphical and auditory tool for neuron-based encoding [73.88751967207419]
  Neuromorphic computing relies on spike-based, energy-efficient communication. We develop a tool to identify suitable configurations for neuron-based encoding of sample-based data into spike trains. The WaLiN-GUI is provided open source and with documentation.
  arXiv  Detail & Related papers  (2023-10-25T20:34:08Z)
• Identifying Interpretable Visual Features in Artificial and Biological Neural Systems [3.604033202771937]
  Single neurons in neural networks are often interpretable in that they represent individual, intuitively meaningful features. Many neurons exhibit $textitmixed selectivity$, i.e., they represent multiple unrelated features. We propose an automated method for quantifying visual interpretability and an approach for finding meaningful directions in network activation space.
  arXiv  Detail & Related papers  (2023-10-17T17:41:28Z)
• Constraints on the design of neuromorphic circuits set by the properties of neural population codes [61.15277741147157]
  In the brain, information is encoded, transmitted and used to inform behaviour. Neuromorphic circuits need to encode information in a way compatible to that used by populations of neuron in the brain.
  arXiv  Detail & Related papers  (2022-12-08T15:16:04Z)
• A Neural Network Based Automated IFT-20 Sensory Neuron Classifier for Caenorhabditis elegans [0.0]
  Cross-organism comparison enables a wide variety of research including whole-brain analysis of functional networks. Recent development of pan-neuronal imaging with single-cell resolution within Caenorhabditis elegans has brought neuron identification, tracking, and activity monitoring all within reach. The principal barrier to high-accuracy neuron identification is that in adult C. elegans, the position of neuronal cell bodies is not stereotyped. I propose an alternative neuronal identification technique using only single-color fluorescent images.
  arXiv  Detail & Related papers  (2022-10-24T00:17:26Z)
• Compositional Explanations of Neurons [52.71742655312625]
  We describe a procedure for explaining neurons in deep representations by identifying compositional logical concepts. We use this procedure to answer several questions on interpretability in models for vision and natural language processing.
  arXiv  Detail & Related papers  (2020-06-24T20:37:05Z)
• Non-linear Neurons with Human-like Apical Dendrite Activations [81.18416067005538]
  We show that a standard neuron followed by our novel apical dendrite activation (ADA) can learn the XOR logical function with 100% accuracy. We conduct experiments on six benchmark data sets from computer vision, signal processing and natural language processing.
  arXiv  Detail & Related papers  (2020-02-02T21:09:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.