Large Language Models for Causal Relations Extraction in Social Media: A Validation Framework for Disaster Intelligence
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910210923167744 |
|---|---|
| author | Jeong, Ujun Vishnubhatla, Saketh Jiang, Bohan Harrison, Andre Raglin, Adrienne Liu, Huan |
| author_facet | Jeong, Ujun Vishnubhatla, Saketh Jiang, Bohan Harrison, Andre Raglin, Adrienne Liu, Huan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_11348 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Large Language Models for Causal Relations Extraction in Social Media: A Validation Framework for Disaster Intelligence Jeong, Ujun Vishnubhatla, Saketh Jiang, Bohan Harrison, Andre Raglin, Adrienne Liu, Huan Computation and Language Artificial Intelligence Information Retrieval Social and Information Networks 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. |
| title | Large Language Models for Causal Relations Extraction in Social Media: A Validation Framework for Disaster Intelligence |
| topic | Computation and Language Artificial Intelligence Information Retrieval Social and Information Networks |
| url | https://arxiv.org/abs/2605.11348 |