用表情符号投票控制回应情感立场，让对话更共情。
EmoStance: Response-Side Affective-Orientation Control for Empathetic Response Generation via Emoji Weak Supervision
- 用多人表情符号投票作为弱监督信号，构建响应情感立场控制空间。
- 在盲评中胜出62.2%，显著提升回应的贴合度与共情感知。
- 适合需要精细化情感表达的对话系统开发者使用。
共情式回复生成不仅需决定说什么，还需判断如何回应对方的情感状态。本文提出响应侧情感立场控制机制，利用多标注者表情符号分布作为弱情感态度证据，而非输出符号或真值标签，以诱导隐式控制空间，近似实现倾听者立场。我们构建了EmojiDialogue数据集，该数据集是EmpatheticDialogues的语句级扩展，包含表情符号投票与置信度评分。提出EmoStance模型，其可建模源端情感表达，从对话上下文与发言者角色预测软性响应立场，并通过连续前缀嵌入引导冻结的指令微调大模型。在20名标注者、800次判断的盲对比较中，EmoStance取得62.2%的决定性胜率，在上下文特异性与感知响应性上提升最明显，且与外部知识方法具有互补性。代码、标注元数据及重建脚本已开源于GitHub：https://github.com/18277390221/EmoStance。
原文摘要 · Abstract (English)
Empathetic response generation requires models to decide not only what to say, but also how to respond to the previous speaker's affective situation. We formulate this as response-side affective-orientation control and use multi-annotator emoji distributions as weak affective--attitudinal evidence, rather than as output symbols or gold labels, to induce a latent control space that operationally approximates listener stance. We construct EmojiDialogue, an utterance-level extension of EmpatheticDialogues with emoji votes and confidence scores, and propose EmoStance, which models source-side affective expression, predicts a soft response-side orientation from dialogue context and speaker roles, and steers a frozen instruction-tuned LLM through continuous prefix embeddings. In blind pairwise evaluation with 20 annotators and 800 judgments, EmoStance achieves a 62.2% decisive win rate, with the clearest gains in contextual specificity and perceived responsiveness, while remaining complementary to external-knowledge methods. Code, annotation metadata, and reconstruction scripts are available in our GitHub repository: https://github.com/18277390221/EmoStance.
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。