生成还是判断？基于范式视角的对话中基于大语言模型（LLM）的情感-原因对抽取
Generation or Judgement? A Paradigm Perspective on LLM-Based Emotion-Cause Pair Extraction in Conversation
浏览论文内容
中文总结 AI 辅助
该研究针对对话情感-原因对抽取，对比LLM的生成与判断范式，发现对级判断更优，引入辅助检索器后在三个数据集上实现F1提升，明确任务分解与候选范围的关键作用。
中文摘要 AI 辅助
对话中的情感-原因对抽取（ECPEC）用于识别这样的话语对：其中一个话语引发了另一个话语所表达的情感。近期基于大语言模型（LLM）的方法以明显不同的粒度形式化ECPEC，范围从生成完整的对集到判断单个候选对。在本文中，我们做出了一个令人惊讶的观察：任务形式化方式会显著影响性能，在所有18组受控对比中，对级判断的表现均优于对话级生成。我们研究了这种范式差距的来源，发现对话级生成所遗漏的许多关系在明确的对查询下仍然可识别，在此查询下，模型可识别92.7%-98.1%的情感-原因关系。这表明LLM能够识别情感-原因关系，但难以发现并返回完整的对集。对级判断减轻了这一负担，尽管其候选排序比共享阈值产生的二元决策更可靠。基于此诊断，我们引入了一个辅助检索器，该检索器有选择地重新检查模糊的边界案例，在三个数据集上实现了0.50-1.46点的一致F1提升，同时推理时间仅为基线范式的1.49倍。这些发现表明，任务分解和候选范围对于有效利用LLM进行ECPEC至关重要。
英文摘要
Emotion-cause pair extraction in conversation (ECPEC) identifies utterance pairs in which one utterance causes an emotion expressed in another. Recent LLM-based approaches formulate ECPEC at markedly different granularities, ranging from generating complete pair sets to judging individual candidate pairs. In this paper, we make the surprising observation that task formulation substantially affects performance, where pair-level judgement outperforms dialogue-level generation in all 18 controlled comparisons. We investigate the sources of this paradigm gap and find that many relations omitted by dialogue-level generation remain recognizable under explicit pair queries, under which the model recognizes 92.7%-98.1% of emotion-cause relations. This suggests that LLMs can recognize emotion-cause relations but struggle to discover and return complete pair sets. Pair-level judgement alleviates this burden, although its candidate rankings are more reliable than the binary decisions produced by a shared threshold. Based on this diagnosis, we introduce an auxiliary retriever that selectively re-examines ambiguous boundary cases, yielding consistent F1 improvements of 0.50-1.46 points across three datasets while maintaining an inference time of only 1.49x that of the baseline paradigm. These findings show that task decomposition and candidate scope are critical to effectively utilizing LLMs for ECPEC.
