“我们希望AI有多敏感？”这项研究聚焦医疗场景下大模型的社交沟通能力，探讨共情、边界与医患信任的平衡点。
arXiv:2608.07511v1 Announce Type: cross Abstract: Background. Effective clinical practice relies heavily on the socio-communicative skills of medical …
AI 代理评论太机械？这个开源技能教 AI 带同理心对话，为开源维护者松口气。
Article URL: https://github.com/danielroe/empathy Comments URL: https://news.ycombinator.com/item?id=49116594 Points: 1 # Comments: 0
AI真的懂不同人群的情绪吗？这项研究实测多款大模型对文本情绪框架的共情对齐程度。
arXiv:2607.27232v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly shaping how we consume information and form our worldv…
通过面部表情感知提示，让LLM辅导系统实时捕捉学生情绪，提升共情辅导效果。
arXiv:2604.15336v2 Announce Type: replace-cross Abstract: Large language models (LLMs) enable increasingly capable tutoring-style conversational agent…
研究发现AI聊天机器人情感支持效果不输人类，甚至更优，刷新对AI共情能力的认知
Article URL: https://www.manchester.ac.uk/about/news/ai-chatbots-can-be-as-effective-as-humans-at-emotional-support--and-sometimes-better/ Comments UR…
大模型竟能当共情教练？练习AI让人类沟通更温暖。
arXiv:2603.15245v2 Announce Type: replace Abstract: Empathy is central to human connection, yet people often struggle to express it effectively. In bl…
跨语言共情与文化适应性基准SPLIT，评估英/乌克兰语LLM的情感自然度与文化理解力。
arXiv:2607.02049v1 Announce Type: cross Abstract: Large Language Models are increasingly deployed in emotional-support contexts and crisis-related sit…
针对药物使用人群的自我污名，用角色化大模型提供共情支持，一项前沿AI研究。
arXiv:2606.23387v1 Announce Type: new Abstract: Self-stigma predicts treatment avoidance and disengagement among people who use drugs (PWUD), yet conv…
LLM共情回应虽广受好评却陷入模板化，新研究揭示其固定表达套路
arXiv:2604.08479v2 Announce Type: replace Abstract: Recent research shows that greater numbers of people are turning to Large Language Models (LLMs) f…
为通用健康查询建模共情适用性，LLM迈向更具人情味的临床沟通。
arXiv:2601.09696v2 Announce Type: replace Abstract: LLMs are increasingly being integrated into clinical workflows, yet they often lack clinical empat…
从信号成本视角重新审视AI共情的适当性，为设计更可信的AI交互提供理论框架
arXiv:2605.31340v1 Announce Type: cross Abstract: The appropriateness of empathy in AI has emerged as a critical concern, as excessive empathy risks s…
利用在线社区反馈优化大语言模型在心理健康支持中的写作辅助，提升共情能力与回复质量。
arXiv:2605.30273v1 Announce Type: cross Abstract: Large language models (LLMs) show promise in generating supportive responses for mental health queri…
研究提出共情提示框架，通过面部表情识别为多模态大模型对话注入非语言情感上下文，提升交互自然度。
arXiv:2510.20743v2 Announce Type: replace-cross Abstract: We present Empathic Prompting, a novel framework for multimodal human-AI interaction that en…