Based on Pre-trained Language Models (PLMs), event coreference resolution
(ECR) systems have demonstrated outstanding performance in clustering
coreferential events across documents. However, the existing system exhibits an
excessive reliance on the `triggers lexical matching' spurious pattern in the
input mention pair text. We formalize the decision-making process of the
baseline ECR system using a Structural Causal Model (SCM), aiming to identify
spurious and causal associations (i.e., rationales) within the ECR task.
Leveraging the debiasing capability of counterfactual data augmentation, we
develop a rationale-centric counterfactual data augmentation method with
LLM-in-the-loop. This method is specialized for pairwise input in the ECR
system, where we conduct direct interventions on triggers and context to
mitigate the spurious association while emphasizing the causation. Our approach
achieves state-of-the-art performance on three popular cross-document ECR
benchmarks and demonstrates robustness in out-of-domain scenarios.

基于预训练语言模型（PLMs），事件共指消解（ECR）系统通过聚类跨文档的语义指示共指事件展现出了出色的性能；然而，现有系统在输入提及对中展现出对 “触发词词汇匹配” 的过度依赖；我们基于结构因果模型（SCM）对基线 ECR 系统的决策过程进行形式化，旨在识别 ECR 任务中的伪因果关联（即依据）；借助反事实数据增强的去偏方法，我们开发了一种以依据为中心的反事实数据增强方法，结合了 LLM 循环；该方法专门针对 ECR 系统的两两输入，在触发词和上下文上进行直接干预，以减少伪关联并强调因果关系；我们的方法在三个流行的跨文档 ECR 基准测试上取得了最先进的性能，并在领域外场景中展现出稳健性。