通过双重反思推理，让对话模型更懂共情。
Reflecting Twice before Speaking with Empathy: Self-Reflective Alternating Inference for Empathy-Aware End-to-End Spoken Dialogue
- 引入交替反思机制，在生成回应前进行共情思考。
- 在多个评测中显著提升对话共情水平，优于基线模型。
- 适合需要情感智能的对话系统研发者使用。
端到端语音语言模型在副语言感知方面具有巨大潜力，众多研究致力于提升其共情对话能力。然而，现有方法大多依赖固定的监督信号，如监督微调中的真实回复或强化学习中的偏好分数，这在建模复杂共情时存在根本局限，因为并无单一“正确”回应，且简单数值评分难以全面捕捉情感表达的细微差别或共情行为的恰当性。为此，我们首先提出 EmpathyEval——一种基于自然语言描述的共情质量评估模型，用于评估语音对话中的共情表现。在此基础上，我们提出 ReEmpathy，一种端到端语音语言模型，采用新颖的共情自反思交替推理机制，将语音回应生成与自由形式的共情相关反思推理交替进行。大量实验表明，ReEmpathy 通过引入反思推理，显著提升了对共情敏感的语音对话性能，为实现更具情感智能和共情意识的人机交互提供了有前景的路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。