LLM中是否存在情绪与修辞神经元？神经元识别与自适应遮蔽用于情绪-修辞预测引导
Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering
AI总结：
本文研究LLM中情绪与修辞神经元的表示机制及内在关联，提出神经元识别框架与自适应遮蔽方法，实现神经元功能的可靠验证，通过神经元调控提升情绪任务与修辞表达的精细控制。
摘要：
准确理解和可控生成情绪与修辞对于增强大语言模型（LLM）的推理能力至关重要。现有研究多依赖外部优化，缺乏对内部表示机制的深入探索，难以在神经元层面实现细粒度引导。部分工作仅关注情绪神经元，忽视修辞神经元及其内在联系。传统神经元遮蔽也表现出反直觉现象，使神经元功能的可靠验证不可行。为解决这些问题，我们系统研究了6种情绪类别和4种核心修辞手法的神经元表示机制和内在关联。我们提出一个整合多维筛选的神经元识别框架，并设计一种结合动态过滤、衰减遮蔽和反馈优化的自适应遮蔽方法，实现神经元功能的可靠因果验证。通过神经元调控，我们实现了非目标句子的定向诱导和通过修辞神经元增强情绪任务。在5个常用数据集上的实验验证了我们方法的有效性，为LLM中情绪与修辞表达的细粒度引导提供了新范式。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
