EMNLP Findings2025
Third-Person Appraisal Agent: Simulating Human Emotional Reasoning in Text with Large Language Models
Simin Hong, Jun Sun, Hongyang Chen
摘要
Emotional reasoning is essential for improving human-AI interactions, particularly in mental health support and empathetic systems. However, current approaches, which primarily map sensory inputs to fixed emotion labels, fail to understand the intricate relationships between motivations, thoughts, and emotions, thereby limiting their ability to generalize across flexible emotional reasoning tasks. To address this, we propose a novel third-person appraisal agent that simulates human-like emotional reasoning through three phases: Primary Appraisal, Secondary Appraisal, and Reappraisal. In the Primary Appraisal phase, a third-person generator powered by a large language model (LLM) infers emotions based on cognitive appraisal theory. The Secondary Appraisal phase uses an evaluator LLM to provide feedback, guiding the generator in refining its predictions. The generator then uses counterfactual reasoning to adjust its process and explore alternative emotional responses. The Reappraisal phase utilizes reinforced fine-tuning (ReFT) by employing a reflective actor-critic framework to further enhance the model's performance and generalization. This process uses reward signals and learns from appraisal trajectories without human annotations. Our approach outperforms baseline LLMs in various emotional reasoning tasks, demonstrating superior generalization and interpretability. To the best of our knowledge, this is the first cognition-based architecture designed to enhance emotional reasoning in LLMs, advancing AI towards human-like emotional understanding. The code is available here.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
已有 1 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。
脉络
引用它的顶会 Paper1
它引用的 Paper18
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu 等ICLR 2022 · 18,833 次引用
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning 等NeurIPS 2023 · 10,924 次引用
- Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan 等NeurIPS 2023 · 5,828 次引用
- Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan 等NeurIPS 2023 · 4,972 次引用
- CEM: Commonsense-Aware Empathetic Response GenerationSahand Sabour, Chujie Zheng, Minlie HuangAAAI 2022 · 196 次引用
相关 Paper
- EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language ModelsYiyang Fang, Wenke Huang, Pei Fu, Yihao Yang 等CVPR 2026 · 4 次引用
- MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent SystemsXuanming Zhang, Yuxuan Chen, Samuel (Min-Hsuan) Yeh, Sharon LiNeurIPS 2025 · 14 次引用
- Consensus-Driven Multi-Agent Cognitive Reasoning for Enhancing the Emotional Intelligence of Large Language ModelsGeng Tu, Dingming Li, Jun Huang, Ruifeng XuAAAI 2026
- ESCA: An Emotional Support Conversation Agent for Enhancing Reasonable Strategy Planning and Effective ExpressionJing Li, Yanxin Luo, Donghong Han, Yimeng Zhan 等AAAI 2026
- Neuro-Sym Supporter: A Thoughtful Emotion Support Agent Integrating Neural and Symbolic Policy LearningMinghui Ma, Bin Guo, Mengqi Chen, Jingqi Liu 等WWW 2026
