从理性答案到情感共鸣：可控情感生成在语言模型中的作用
From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models
AI总结：
针对大语言模型情感表达不一致的问题，提出基于情感向量的可控情感生成框架，通过注入隐藏状态实现无需训练的细粒度情感调制，在保持语义的同时增强情感表达，优于现有基线。
摘要：
目的：情感是人类沟通的基本组成部分，在教育、医疗保健和心理健康等领域塑造着理解、信任和参与。虽然大型语言模型（LLMs）展现出强大的推理和知识生成能力，但它们仍难以以一致、可控且情境适当的方式表达情感。这一局限性限制了它们在真实人机交互中的潜力。方法：我们提出了一种基于情感向量（EVs）的可控情感生成框架——情感向量是从中性响应与情感条件响应之间的内部激活偏移中导出的潜在表示。通过在推理过程中将这些向量注入预训练LLMs的隐藏状态，我们的方法能够在不进行任何额外训练或架构修改的情况下，实现对情感色调的细粒度、连续调制。我们进一步提供了理论分析，证明情感向量引导在保持语义保真度和语言流畅性的同时，增强了情感表达性。结果：跨多个LLM家族的广泛实验表明，所提出的方法实现了一致的情感对齐、稳定的主题保持和可控的情感强度。与现有的基于提示和基于微调的基线方法相比，我们的方法展现出更优的灵活性和泛化能力。结论：情感向量（EV）引导提供了一种高效且可解释的方式，在大型语言模型中架起理性推理与情感理解的桥梁，为构建能够实现更自然人机交互的情感共鸣AI系统提供了一个有前景的方向。
英文摘要：
Purpose: Emotion is a fundamental component of human communication, shaping understanding, trust, and engagement across domains such as education, healthcare, and mental health. While large language models (LLMs) exhibit strong reasoning and knowledge generation capabilities, they still struggle to express emotions in a consistent, controllable, and contextually appropriate manner. This limitation restricts their potential for authentic human-AI interaction. Methods: We propose a controllable emotion generation framework based on Emotion Vectors (EVs) - latent representations derived from internal activation shifts between neutral and emotion-conditioned responses. By injecting these vectors into the hidden states of pretrained LLMs during inference, our method enables fine-grained, continuous modulation of emotional tone without any additional training or architectural modification. We further provide theoretical analysis proving that EV steering enhances emotional expressivity while maintaining semantic fidelity and linguistic fluency. Results: Extensive experiments across multiple LLM families show that the proposed approach achieves consistent emotional alignment, stable topic adherence, and controllable affect intensity. Compared with existing prompt-based and fine-tuning-based baselines, our method demonstrates superior flexibility and generalizability. Conclusion: Emotion Vector (EV) steering provides an efficient and interpretable means of bridging rational reasoning and affective understanding in large language models, offering a promising direction for building emotionally resonant AI systems capable of more natural human-machine interaction.
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。
