在富有同理心之前两次反思：用于富有同理心的端到端语音对话的自我反思交替推理
Reflecting Twice before Speaking with Empathy: Self-Reflective Alternating Inference for Empathy-Aware End-to-End Spoken Dialogue
AI总结：
ReEmpathy通过自我反思交替推理机制提升语音对话的同理心表现，实现更情感智能的人机交互。
摘要：
端到端语音语言模型（SLMs）在语调感知方面具有巨大潜力，许多研究旨在增强其能力，特别是对于富有同理心的对话。然而，当前方法大多依赖于刚性的监督信号，如监督微调中的真实响应或强化学习中的偏好分数。这种依赖在建模复杂的同理心方面本质上是有限的，因为没有单一的'正确'响应，简单的数值分数无法完全捕捉情感表达的细微差别或同理心行为的适当性。为了解决这些限制，我们依次引入EmpathyEval，一个基于描述性自然语言的评估模型，用于评估语音对话中的同理心质量。在此基础上，我们提出了ReEmpathy，一个端到端的SLM，通过一种新的富有同理心的自我反思交替推理机制来增强富有同理心的对话，该机制将语音响应生成与自由形式的、与同理心相关的反思推理交织在一起。广泛的实验表明，ReEmpathy通过使反思推理成为可能，显著提高了对同理心敏感的语音对话，提供了一种朝着更加情感智能和富有同理心的人机交互的有希望的方法。
英文摘要：
End-to-end Spoken Language Models (SLMs) hold great potential for paralinguistic perception, and numerous studies have aimed to enhance their capabilities, particularly for empathetic dialogue. However, current approaches largely depend on rigid supervised signals, such as ground-truth response in supervised fine-tuning or preference scores in reinforcement learning. Such reliance is fundamentally limited for modeling complex empathy, as there is no single "correct" response and a simple numerical score cannot fully capture the nuances of emotional expression or the appropriateness of empathetic behavior. To address these limitations, we sequentially introduce EmpathyEval, a descriptive natural-language-based evaluation model for assessing empathetic quality in spoken dialogues. Building upon EmpathyEval, we propose ReEmpathy, an end-to-end SLM that enhances empathetic dialogue through a novel Empathetic Self-Reflective Alternating Inference mechanism, which interleaves spoken response generation with free-form, empathy-related reflective reasoning. Extensive experiments demonstrate that ReEmpathy substantially improves empathy-sensitive spoken dialogue by enabling reflective reasoning, offering a promising approach toward more emotionally intelligent and empathy-aware human-computer interactions.
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。
