<ul><li>Automated causal loop diagram (CLD) generation using large language models (LLMs) is introduced.</li><li>LLMs can make inferences and build CLDs from dynamic hypotheses using a digraph structure.</li><li>Four combinations of prompting techniques were evaluated and compared against expert-labeled CLDs.</li><li>Results show that LLMs can generate high-quality CLDs, accelerating the CLD creation process.</li></ul>

Leveraging Large Language Models for Automated Causal Loop Diagram Generation: Enhancing System Dynamics Modeling through Curated Prompting Techniques

Discover more