ECR-Chain: 通过推理链提升生成式语言模型的情绪-原因推理能力
ECR-Chain: Advancing Generative Language Models to Better Emotion-Cause Reasoners through Reasoning Chains
AI总结：
针对当前因果情绪蕴含（CEE）任务忽视情绪产生过程、缺乏可解释性的问题，本研究提出ECR-Chain逐步推理方法，通过少样本提示提升ChatGPT的CEE性能，还构建ECR-Chain数据集助力Vicuna-7B取得SOTA，实现了可解释的情绪-原因推理。
摘要：
理解情绪产生过程对分析情绪背后的原因至关重要。因果情绪蕴含（Causal Emotion Entailment, CEE）是一项情绪理解任务，旨在识别对话中引发目标话语所表达情绪的因果话语。然而，当前CEE领域的研究主要聚焦于建模对话中的语义与情绪交互，忽视了对情绪产生过程的探索，这阻碍了模型对情绪的深度理解，限制了其生成可解释预测的能力。本研究受认知评价理论中“刺激-评价-情绪”的情绪产生过程启发，提出了一种逐步推理方法——情绪-原因推理链（Emotion-Cause Reasoning Chain, ECR-Chain），用于从对话中的目标情绪表达推断刺激来源。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任务上的性能。我们进一步提出了一种自动化构建流程，利用ChatGPT构建ECR-Chain数据集，该数据集可通过监督训练增强小模型的推理能力，并助力Vicuna-7B模型取得了CEE任务的最优性能。此外，我们的方法能够使这些生成式语言模型以可解释的方式有效开展情绪-原因推理。我们的代码、数据及更多细节详见https://github.com/hzp3517/ECR-Chain。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
