EMNLP Findings2025
Third-Person Appraisal Agent: Simulating Human Emotional Reasoning in Text with Large Language Models
Simin Hong, Jun Sun, Hongyang Chen
Abstract
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on18
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning et al.NeurIPS 2023 · 10,924 citations
- Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
- Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan et al.NeurIPS 2023 · 4,972 citations
- CEM: Commonsense-Aware Empathetic Response GenerationSahand Sabour, Chujie Zheng, Minlie HuangAAAI 2022 · 196 citations
Related papers
- EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language ModelsYiyang Fang, Wenke Huang, Pei Fu, Yihao Yang et al.CVPR 2026 · 4 citations
- MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent SystemsXuanming Zhang, Yuxuan Chen, Samuel (Min-Hsuan) Yeh, Sharon LiNeurIPS 2025 · 14 citations
- 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 et al.AAAI 2026
- Neuro-Sym Supporter: A Thoughtful Emotion Support Agent Integrating Neural and Symbolic Policy LearningMinghui Ma, Bin Guo, Mengqi Chen, Jingqi Liu et al.WWW 2026
