Emotion-Cause Pair Extraction (ECPE) involves extracting clause pairs representing emotions and their causes in a document. Existing methods tend to overfit spurious correlations, such as positional bias in existing benchmark datasets, rather than capturing semantic features. Inspired by recent work, we explore leveraging large language model (LLM) to address ECPE task without additional training. Despite strong capabilities, LLMs suffer from uncontrollable outputs, resulting in mediocre performance. To address this, we introduce chain-of-thought to mimic human cognitive process and propose the Decomposed Emotion-Cause Chain (DECC) framework. Combining inducing inference and logical pruning, DECC guides LLMs to tackle ECPE task. We further enhance the framework by incorporating in-context learning. Experiment results demonstrate the strength of DECC compared to state-of-the-art supervised fine-tuning methods. Finally, we analyze the effectiveness of each component and the robustness of the method in various scenarios, including different LLM bases, rebalanced datasets, and multi-pair extraction.

翻译：情感-原因对抽取（ECPE）任务旨在提取文档中表示情感及其原因的从句对。现有方法倾向于过拟合虚假相关性（如现有基准数据集中的位置偏差），而非捕捉语义特征。受近期研究启发，我们探索利用大语言模型（LLM）在不进行额外训练的情况下解决ECPE任务。尽管LLM具备强大能力，但其输出不可控，导致性能平庸。为应对这一挑战，我们引入思维链以模拟人类认知过程，并提出分解情感-原因链（DECC）框架。结合归纳推理与逻辑剪枝，DECC引导LLM处理ECPE任务。我们进一步通过引入上下文学习增强该框架。实验结果表明，DECC相较于最先进的监督微调方法具有显著优势。最后，我们分析了各组成部分的有效性及该方法在不同场景（包括不同LLM基座、均衡数据集与多对抽取）中的鲁棒性。