# Large Language Models for Causal Relations Extraction in Social Media: A Validation Framework for Disaster Intelligence

arXiv: https://arxiv.org/abs/2605.11348 · HTML: https://mlsanity.com/paper/2605.11348/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 39 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 16 of 16)

- [Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction](https://mlsanity.com/paper/2106.09232/) (2021)
- [CrisisMMD: Multimodal Twitter Datasets from Natural Disasters](https://mlsanity.com/paper/1805.00713/) (2018)
- [Universal Information Extraction as Unified Semantic Matching](https://mlsanity.com/paper/2301.03282/) (2023)
- [Twitter as a Lifeline: Human-annotated Twitter Corpora for NLP of Crisis-related Messages](https://mlsanity.com/paper/1605.05894/) (2016)
- [HumAID: Human-Annotated Disaster Incidents Data from Twitter with Deep Learning Benchmarks](https://mlsanity.com/paper/2104.03090/) (2021)
- [Nothing Stands Alone: Relational Fake News Detection with Hypergraph Neural Networks](https://mlsanity.com/paper/2212.12621/) (2022)
- [Exploring Platform Migration Patterns between Twitter and Mastodon: A User Behavior Study](https://mlsanity.com/paper/2305.09196/) (2023)
- [Can Large Language Models Infer Causal Relationships from Real-World Text?](https://mlsanity.com/paper/2505.18931/) (2025)
- [BlueTempNet: A Temporal Multi-network Dataset of Social Interactions in Bluesky Social](https://mlsanity.com/paper/2407.17451/) (2024)
- [Paths to Causality: Finding Informative Subgraphs Within Knowledge Graphs for Knowledge-Based Causal Discovery](https://mlsanity.com/paper/2506.08771/) (2025)
- [Fediverse Sharing: Cross-Platform Interaction Dynamics between Threads and Mastodon Users](https://mlsanity.com/paper/2502.17926/) (2025)
- [Navigating Decentralized Online Social Networks: An Overview of Technical and Societal Challenges in Architectural Choices](https://mlsanity.com/paper/2504.00071/) (2025)
- [Assessing On-the-Ground Disaster Impact Using Online Data Sources](https://mlsanity.com/paper/2509.11634/) (2025)
- [An Interventional Approach to Real-Time Disaster Assessment via Causal Attribution](https://mlsanity.com/paper/2509.11676/) (2025)
- [CAMO: Causality-Guided Adversarial Multimodal Domain Generalization for Crisis Classification](https://mlsanity.com/paper/2512.08071/) (2025)
- [SERE: Structural Example Retrieval for Enhancing LLMs in Event Causality Identification](https://mlsanity.com/paper/2605.03701/) (2026)

## Abstract (arXiv)

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.