Large Language Models (LLMs) and Causality Extraction from Text
Open Access
- 14 May 2025
- journal article
- Published by University of Florida George A Smathers Libraries in Pediatrics in Review
- Vol. 38
Abstract
This tutorial explores the application of Large Language Models (LLMs), such as BERT, LLAMA, andGPT-3.5/4, to the extraction of causality from text documents, including identifying causes, effects, and actions in diverse texts, such as business, medical, and newswire domains. We also address challenges relatedto data availability and quality, such as varying definitions of causality. Causality extraction plays a crucial role in natural language understanding, particularly for building structured representations of medical and technical texts and for multimodal question answering. Participants will gain access to example code and links to related repositories. Beyond causality extraction, thesession will connect these tasks to broader themes, such as the mathematics of hallucinations in generative models and best practices for effective prompting. Designed for participants with some familiarity with machine learning or natural language processing (NLP), and ideally LLMs, the tutorial should be both accessible and highly relevant.Keywords
This publication has 5 references indexed in Scilit:
- On the relation between K–L divergence and transfer learning performance on causality extraction tasksNatural Language Processing Journal, 2024
- Text to Causal Knowledge Graph: A Framework to Synthesize Knowledge from Unstructured Business Texts into Causal GraphsInformation, 2023
- The Representation of Causality and Causation with Ontologies: A Systematic Literature ReviewOnline Journal of Public Health Informatics, 2022
- The seven tools of causal inference, with reflections on machine learningCommunications of the ACM, 2019
- Probabilistic Causation2017