发表机构
ShanghaiTech University（上海科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对共情回应生成的回应端情感倾向控制问题，提出基于表情符号弱监督的EmoStance模型，在盲法评估中取得62.2%的决定性胜率，提升了回应的上下文特异性与感知回应性。
AI 中文摘要
共情回应生成要求模型不仅要决定说什么，还要决定如何回应前一说话者的情感处境。我们将此问题形式化为回应端情感倾向控制，使用多标注者的表情符号分布作为弱情感态度证据，而非输出符号或黄金标签，来诱导近似听者立场的潜在控制空间。我们构建了EmojiDialogue，这是EmpatheticDialogues的话语级扩展版本，包含表情符号投票和置信度分数；并提出了EmoStance模型，该模型对源端情感表达进行建模，从对话上下文和说话者角色预测软回应端倾向，通过连续前缀嵌入引导冻结的指令调优大语言模型（LLM）。在20名标注者参与的盲法成对评估中，共800次判断，EmoStance达到62.2%的决定性胜率，在上下文特异性和感知回应性方面的提升最为显著，同时与外部知识方法互补。代码、标注元数据和重构脚本可在我们的GitHub仓库获取：this https URL。
英文摘要
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.
CommentsAccepted to the Main Conference of EMNLP 2026
