通过发散与收敛推理，提升零样本事件检测的覆盖率和准确率。
DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning
- 分两阶段：先自由发现事件（发散），再按规则约束对齐（收敛）
- 在6个数据集上平均提升4-7% F1，优于现有方法
- 适合需要高覆盖且精准识别事件的领域应用
零样本事件检测（ED）旨在无需训练数据的情况下识别自然语言中的事件提及，对专业领域的文档理解至关重要。由于复杂的事件本体、领域特定触发词提取及结构化需求，传统大模型在零样本ED中面临性能瓶颈。为此，本文提出DiCoRe框架，采用发散-收敛式推理机制，将任务分解为两个阶段：Dreamer模块通过开放式的事件探索实现发散推理，提升事件覆盖范围；Grounder模块则利用有限状态机引导的约束解码进行收敛推理，使自由生成的结果符合任务指令。此外，引入LLM-Judge对最终输出进行验证，保障精度。在五个领域、六个数据集及九种LLM上的实验表明，DiCoRe consistently 超越先前零样本、迁移学习及推理基线，平均F1提升4-7%，确立其作为强零样本事件检测框架的地位。
原文摘要 · Abstract (English)
Zero-shot Event Detection (ED), the task of identifying event mentions in natural language text without any training data, is critical for document understanding in specialized domains. Understanding the complex event ontology, extracting domain-specific triggers from the passage, and structuring them appropriately overloads and limits the utility of Large Language Models (LLMs) for zero-shot ED. To this end, we propose DiCoRe, a divergent-convergent reasoning framework that decouples the task of ED using Dreamer and Grounder. Dreamer encourages divergent reasoning through open-ended event discovery, which helps to boost event coverage. Conversely, Grounder introduces convergent reasoning to align the free-form predictions with the task-specific instructions using finite-state machine guided constrained decoding. Additionally, an LLM-Judge verifies the final outputs to ensure high precision. Through extensive experiments on six datasets across five domains and nine LLMs, we demonstrate how DiCoRe consistently outperforms prior zero-shot, transfer-learning, and reasoning baselines, achieving 4-7% average F1 gains over the best baseline -- establishing DiCoRe as a strong zero-shot ED framework.
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。