Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering

• URL: http://arxiv.org/abs/2604.17255v1
• Date: Sun, 19 Apr 2026 04:41:08 GMT
• Title: Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering
• Abstract summary: Existing studies mostly rely on external optimizations, lacking in-depth exploration of internal representation mechanisms.<n>We propose a neuron identification framework that integrates multi-dimensional screening, and design an adaptive masking method.<n>We achieve directed induction of non-target sentences and enhancement of emotion tasks via rhetoric neurons.
• Score: 28.166264440634553
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate comprehension and controllable generation of emotion and rhetoric are pivotal for enhancing the reasoning capabilities of large language models (LLMs). Existing studies mostly rely on external optimizations, lacking in-depth exploration of internal representation mechanisms, thus failing to achieve fine-grained steering at the neuron level. A handful of works on neurons are confined to emotions, neglecting rhetoric neurons and their intrinsic connections. Traditional neuron masking also exhibits counterintuitive phenomena, making reliable verification of neuron functionality infeasible. To address these issues, we systematically investigate the neurons representation mechanisms and inherent associations of 6 emotion categories and 4 core rhetorical devices. We propose a neuron identification framework that integrates multi-dimensional screening, and design an adaptive masking method incorporating dynamic filtering, attenuation masking, and feedback optimization, enabling reliable causal validation of neuron functionality.Through neuron regulation, we achieve directed induction of non-target sentences and enhancement of emotion tasks via rhetoric neurons. Experiments on 5 commonly used datasets validate the effectiveness of our method, providing a novel paradigm for the fine-grained steering of emotion and rhetoric expressions in LLMs.

Related papers

• From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models [10.052877942432783]
  HONES is a gradient-free framework for task-aware neuron attribution and steering in vision-language models.<n>We show that HONES outperforms existing methods in identifying task-critical neurons and improves model performance after steering.
  arXiv  Detail & Related papers  (2026-04-20T08:21:06Z)
• 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)
• Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models [8.550786156000461]
  We present the first neuron-level interpretability study of emotion-sensitive neurons (ESNs) in large audio-language models (LALMs)<n>We compare frequency-, entropy-, magnitude-, and contrast-based neuron selectors on multiple emotion recognition benchmarks.<n>Using inference-time interventions, we reveal a consistent emotion-specific signature.
  arXiv  Detail & Related papers  (2026-01-06T15:46:35Z)
• NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models [14.630626774362606]
  Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content.<n>We propose a novel approach to induce disalignment by identifying and modifying the neurons responsible for safety constraints.
  arXiv  Detail & Related papers  (2025-04-29T05:49:35Z)
• Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution [16.460751105639623]
  We show that even highly salient neurons consistently exhibit polysemantic behavior.<n>This observation motivates a shift from neuron attribution to range-based interpretation.<n>We introduce NeuronLens, a novel range-based interpretation and manipulation framework.
  arXiv  Detail & Related papers  (2025-02-04T03:33:55Z)
• Interpretable Dual-Filter Fuzzy Neural Networks for Affective Brain-Computer Interfaces [25.445687764717167]
  We present iFuzzyAffectDuo, a novel model that integrates a dual-filter fuzzy neural network architecture for improved detection and interpretation of emotional states.<n>We validate our approach across three neuroimaging datasets using functional Near-Infrared Spectroscopy (fNIRS) and Electroencephalography (EEG)
  arXiv  Detail & Related papers  (2025-01-29T14:31:57Z)
• Brain-like Functional Organization within Large Language Models [58.93629121400745]
  The human brain has long inspired the pursuit of artificial intelligence (AI) Recent neuroimaging studies provide compelling evidence of alignment between the computational representation of artificial neural networks (ANNs) and the neural responses of the human brain to stimuli. In this study, we bridge this gap by directly coupling sub-groups of artificial neurons with functional brain networks (FBNs) This framework links the AN sub-groups to FBNs, enabling the delineation of brain-like functional organization within large language models (LLMs)
  arXiv  Detail & Related papers  (2024-10-25T13:15:17Z)
• Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks [74.3099028063756]
  We develop a new method with neuronal operations based on lateral connections and Hebbian learning. We show that Hebbian and anti-Hebbian learning on recurrent lateral connections can effectively extract the principal subspace of neural activities. Our method consistently solves for spiking neural networks with nearly zero forgetting.
  arXiv  Detail & Related papers  (2024-02-19T09:29:37Z)
• Fast gradient-free activation maximization for neurons in spiking neural networks [5.805438104063613]
  We present a framework with an efficient design for such a loop. We track changes in the optimal stimuli for artificial neurons during training. This formation of refined optimal stimuli is associated with an increase in classification accuracy.
  arXiv  Detail & Related papers  (2023-12-28T18:30:13Z)
• Redundancy and Concept Analysis for Code-trained Language Models [5.726842555987591]
  Code-trained language models have proven to be highly effective for various code intelligence tasks. They can be challenging to train and deploy for many software engineering applications due to computational bottlenecks and memory constraints. We perform the first neuron-level analysis for source code models to identify textitimportant neurons within latent representations.
  arXiv  Detail & Related papers  (2023-05-01T15:22:41Z)
• 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)
• 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.