Large Language Models for Causal Relations Extraction in Social Media: A Validation Framework for Disaster Intelligence
For disaster response teams, this work evaluates the feasibility of using LLMs for causal extraction from noisy social media, but the findings are preliminary and lack quantitative validation.
The paper investigates whether LLMs can extract causal relations from disaster-related social media posts, proposing an evaluation framework that compares LLM-generated causal graphs with reference graphs from disaster reports. Results show both potential and risks, but no concrete performance numbers are provided.
During disasters, extracting causal relations from social media can strengthen situational awareness by identifying factors linked to casualties, physical damage, infrastructure disruption, and cascading impacts. However, disaster-related posts are often informal, fragmented, and context-dependent, and they may describe personal experiences rather than explicit causal relations. In this work, we examine whether Large Language Models (LLMs) can effectively extract causal relations from disaster-related social media posts. To this end, we (1) propose an expert-grounded evaluation framework that compares LLM-generated causal graphs with reference graphs derived from disaster-specific reports and (2) assess whether the extracted relations are supported by post-event evidence or instead reflect model priors. Our findings highlight both the potential and risks of using LLMs for causal relation extraction in disaster decision-support systems.