SERE: Structural Example Retrieval for Enhancing LLMs in Event Causality Identification

ArXi:2605.03701v1 Announce Type: cross Event Causality Identification (ECI) requires models to determine whether a given pair of events in a context exhibits a causal relationship. While Large Language Models (LLMs) have nstrated strong performance across various NLP tasks, their effectiveness in ECI remains limited due to biases in causal reasoning, often leading to overprediction of causal relationships (causal hallucination