让大模型同时具备理性与共情能力，对话更懂人心。
EmoLLM: Appraisal-Grounded Cognitive-Emotional Co-Reasoning in Large Language Models
- 用显式评估图结构梳理用户需求与情绪
- 多轮角色扮演训练，强化情感回应效果
- 适合心理支持、咨询等需共情的场景
大型语言模型（LLMs）展现出强大的认知智能（IQ），但在情感支持、技术协助和咨询等真实场景中，还需情绪智能（EQ）以生成既准确又恰当的回应。有效对话依赖于对用户需求、目标和应对能力的恰当评估。受评估理论启发，我们提出EmoLLM，一种基于评估的智商/情商协同推理框架。EmoLLM通过显式的评估推理图（ARG）在生成回复前，结构化地整合上下文事实、用户需求推断、评估维度、情绪状态与应答策略。我们在多轮角色扮演环境中采用强化学习训练该模型，反向视角推理提供基于预测用户反应的奖励信号。在多种对话场景中，EmoLLM在情绪状态改善与回复质量上优于强基线模型，同时保持了高事实可靠性。
原文摘要 · Abstract (English)
Large language models (LLMs) demonstrate strong cognitive intelligence (IQ), yet many real-world interactions also require emotional intelligence (EQ) to produce responses that are both factually reliable and emotionally appropriate. In settings such as emotional support, technical assistance, and consultation, effective dialogue depends on how situations are appraised with respect to the user's needs, goals, and coping capacity. Inspired by appraisal theory, we propose EmoLLM, an appraisal-grounded framework for IQ/EQ co-reasoning in dialogue. EmoLLM uses an explicit Appraisal Reasoning Graph (ARG) to structure intermediate reasoning over contextual facts, inferred user needs, appraisal dimensions, emotional states, and response strategies before generating a reply. We train EmoLLM in a multi-turn role-play environment with reinforcement learning, where reverse-perspective reasoning provides reward signals based on predicted user-side consequences of responses. Across diverse dialogue settings, EmoLLM improves emotional state outcomes and response quality over strong baselines while preserving strong factual reliability.
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。