Emergency response is a safety-critical public governance task that demands accurate and timely decision-making based on complex event information. This process involves multiple stages, including information collection, integration, analysis, risk assessment, and decision recommendation. Existing research has predominantly concentrated on the earlier stages, while studies focusing on the decision support phase remain underexplored, primarily due to the lack of suitable datasets for reliable and compliance-aware decision-oriented modeling and evaluation. To bridge this gap, we introduce the first real-world Emergency Decision-Making dataset EDM-Bench, comprising 1,179 instances spanning diverse task formats, including judgment, choice, short-answer, and structured emergency report generation. We also construct a structured rule repository, EDM-R², which contains 3,406 parsed emergency regulations to enhance decision reliability. Building on these resources, we propose a rule-enhanced reasoning framework, R³V-EDM, which integrates external regulatory knowledge with constrained inference mechanisms to improve both decision safety and interpretability. Extensive experiments demonstrate the inherent complexity of emergency decision-making and validate the effectiveness of our approach in enabling more reliable and trustworthy decisions.

Event extraction (EE) is a critical task in natural language processing, yet deploying a practical EE system remains challenging. On one hand, powerful large language models (LLMs) currently show poor performance because EE task is more complex than other tasks. On the other hand, state-of-the-art (SOTA) small language models (SLMs) for EE tasks are typically developed through fine-tuning, lack flexibility, and have considerable room for improvement. We propose an approach, **L**LMs-as-**C**orrector for **E**vent **E**xtraction (**LC4EE**), aiming to leverage the superior extraction capability of SLMs and the instruction-following ability of LLMs to construct a robust and highly available EE system. By utilizing LLMs to identify and correct errors of SLMs predictions based on automatically generated feedback information, EE performances can be improved significantly. Experimental results on the representative datasets ACE2005 and MAVEN-Arg for Event Detection (ED) and EE tasks validated the effectiveness of our method.