Enhancing Large Language Model with Decomposed Reasoning for Emotion Cause Pair Extraction
This addresses the problem of extracting emotion-cause pairs in text for natural language processing applications, but it is incremental as it builds on existing LLM and reasoning techniques.
The paper tackled the Emotion-Cause Pair Extraction (ECPE) task by proposing the Decomposed Emotion-Cause Chain (DECC) framework, which uses chain-of-thought reasoning and in-context learning with large language models to improve performance over state-of-the-art supervised methods.
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.