融合智能体与序列标注，提升事件抽取的准确率与召回率。
Reflective Agreement: Combining Self-Mixture of Agents with a Sequence Tagger for Robust Event Extraction
- 用多个智能体协作并行推理，通过共识机制增强可靠性。
- 在三个基准数据集上超越现有最优方法，显著提升召回率。
- 适合需要高精度事件抽取的金融、舆情等场景使用。
事件抽取（EE）旨在从非结构化文本中自动识别并提取事件的触发词、类型及论元等结构化信息。传统判别模型虽精度高但召回率有限，尤其对细微或罕见事件表现不佳；而基于大语言模型（LLM）的生成式方法虽具备更强语义灵活性和召回能力，却存在幻觉与预测不一致问题。为此，本文提出基于共识的反思推理系统（ARIS），融合自混合智能体与判别性序列标注器。ARIS通过结构化模型共识、置信度过滤及LLM反思推理模块，有效解决歧义，提升整体预测质量。此外，我们还探索了分解式指令微调以增强LLM对事件抽取的理解。实验表明，该方法在三个基准数据集上均优于现有最先进方法。
原文摘要 · Abstract (English)
Event Extraction (EE) involves automatically identifying and extracting structured information about events from unstructured text, including triggers, event types, and arguments. Traditional discriminative models demonstrate high precision but often exhibit limited recall, particularly for nuanced or infrequent events. Conversely, generative approaches leveraging Large Language Models (LLMs) provide higher semantic flexibility and recall but suffer from hallucinations and inconsistent predictions. To address these challenges, we propose Agreement-based Reflective Inference System (ARIS), a hybrid approach combining a Self Mixture of Agents with a discriminative sequence tagger. ARIS explicitly leverages structured model consensus, confidence-based filtering, and an LLM reflective inference module to reliably resolve ambiguities and enhance overall event prediction quality. We further investigate decomposed instruction fine-tuning for enhanced LLM event extraction understanding. Experiments demonstrate our approach outperforms existing state-of-the-art event extraction methods across three benchmark datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。