SELF-EMO：从识别到一致表达的情感自我进化
SELF-EMO: Emotional Self-Evolution from Recognition to Consistent Expression
AI总结：
SELF-EMO通过引入情感理解和表达辅助任务，结合角色自博弈机制和数据飞轮机制，实现情感识别与表达的自我进化，实验表明其在多个数据集上均取得最优性能。
摘要：
情感对话识别（ERC）已成为大型语言模型（LLMs）在以人为本的交互中的一项基本能力。除了准确识别外，连贯的情感表达也至关重要，但两者都受限于高质量标注数据的稀缺性和静态性。本文提出SELF-EMO，一种基于'更好的情感预测导致更一致的情感回应'假设的自我进化框架。我们引入了情感理解和表达两个辅助任务，并设计了基于角色的自博弈范式，使模型同时扮演情感识别者和对话回应者。通过迭代交互，模型生成多样化的对话轨迹，实现可扩展的数据生成。为确保质量，我们采用数据飞轮机制，通过平滑的IoU基于奖励过滤候选预测和回应，并将选定样本反馈进行持续自我改进，无需外部监督。我们进一步开发了SELF-GRPO，一种通过多标签对齐奖励和群体一致性信号稳定优化的强化学习算法。在IEMOCAP、MELD和EmoryNLP数据集上的实验表明，SELF-EMO在多个数据集上均取得最优性能，相比Qwen3-4B提升6.33%，Qwen3-8B提升8.54%，证明了其有效性与泛化能力。
英文摘要：
Emotion Recognition in Conversation (ERC) has become a fundamental capability for large language models (LLMs) in human-centric interaction. Beyond accurate recognition, coherent emotional expression is also crucial, yet both are limited by the scarcity and static nature of high-quality annotated data. In this work, we propose SELF-EMO, a self-evolution framework grounded in the hypothesis that better emotion prediction leads to more consistent emotional responses. We introduce two auxiliary tasks, emotional understanding and emotional expression, and design a role-based self-play paradigm where the model acts as both an emotion recognizer and a dialogue responder. Through iterative interactions, the model generates diverse conversational trajectories, enabling scalable data generation. To ensure quality, we adopt a data flywheel mechanism that filters candidate predictions and responses using a smoothed IoU-based reward and feeds selected samples back for continuous self-improvement without external supervision. We further develop SELF-GRPO, a reinforcement learning algorithm that stabilizes optimization with multi-label alignment rewards and group-level consistency signals. Experiments on IEMOCAP, MELD, and EmoryNLP show that SELF-EMO achieves state-of-the-art performance, improving accuracy by +6.33% on Qwen3-4B and +8.54% on Qwen3-8B, demonstrating strong effectiveness and generalization.
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。
