Understanding the process of emotion generation is crucial for analyzing the causes behind emotions. Causal Emotion Entailment (CEE), an emotion-understanding task, aims to identify the causal utterances in a conversation that stimulate the emotions expressed in a target utterance. However, current works in CEE mainly focus on modeling semantic and emotional interactions in conversations, neglecting the exploration of the emotion-generation process. This hinders the models from deeply understanding emotions, restricting their ability to produce explainable predictions. In this work, inspired by the emotion generation process of "stimulus-appraisal-emotion" in the cognitive appraisal theory, we introduce a step-by-step reasoning method, Emotion-Cause Reasoning Chain (ECR-Chain), to infer the stimulus from the target emotional expressions in conversations. Specifically, we first introduce the ECR-Chain to ChatGPT via few-shot prompting, which significantly improves its performance on the CEE task. We further propose an automated construction process to utilize ChatGPT in building an ECR-Chain set, which can enhance the reasoning abilities of smaller models through supervised training and assist the Vicuna-7B model in achieving state-of-the-art CEE performance. Moreover, our methods can enable these generative language models to effectively perform emotion-cause reasoning in an explainable manner. Our code, data and more details are at https://github.com/hzp3517/ECR-Chain.

翻译：理解情感生成过程对于分析情感背后的原因至关重要。因果情感蕴含（CEE）作为一项情感理解任务，旨在识别对话中激发目标话语所表达情感的因果话语。然而，当前CEE相关研究主要聚焦于建模对话中的语义与情感交互，忽视了情感生成过程的探索。这阻碍了模型对情感的深层理解，限制了其生成可解释预测的能力。受认知评价理论中"刺激-评价-情感"的情感生成过程启发，本文提出一种逐步推理方法——情感-原因推理链（ECR-Chain），用于从对话中的目标情感表达推断刺激因素。具体而言，我们首先通过少样本提示将ECR-Chain引入ChatGPT，显著提升了其在CEE任务中的性能。进一步提出自动化构建流程，利用ChatGPT构建ECR-Chain数据集，通过监督训练增强小型模型的推理能力，并帮助Vicuna-7B模型达到CEE任务的最优性能。此外，我们的方法能够使生成式语言模型以可解释方式有效执行情感-原因推理。相关代码、数据及更多细节参见https://github.com/hzp3517/ECR-Chain。