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

📅 2025-03-23
📈 Citations: 1
Influential: 0
📄 PDF

career value

206K/year
🤖 AI Summary
Causal Loop Diagram (CLD) construction in system dynamics suffers from low efficiency and high entry barriers for novices. Method: This paper proposes the first stepwise prompt engineering framework tailored for CLD generation, leveraging large language models (LLMs) to automatically map textual dynamic hypotheses into structured CLDs. The approach integrates chain-of-thought reasoning, role-guided prompting, and domain-specific constraints, representing CLDs as standard directed graphs; it is fine-tuned and evaluated on a textbook-based system dynamics dataset. Contribution/Results: Experiments show that the automatically generated CLDs achieve 89% agreement with expert-built diagrams on simple dynamic structures, substantially reducing modeling time. This work establishes the first end-to-end, accurate, interpretable, and domain-aligned natural-language-to-CLD generation pipeline, empirically validating the feasibility and practical utility of LLMs in automating system modeling.

Technology Category

Application Category

📝 Abstract
Transforming a dynamic hypothesis into a causal loop diagram (CLD) is crucial for System Dynamics Modelling. Extracting key variables and causal relationships from text to build a CLD is often challenging and time-consuming for novice modelers, limiting SD tool adoption. This paper introduces and tests a method for automating the translation of dynamic hypotheses into CLDs using large language models (LLMs) with curated prompting techniques. We first describe how LLMs work and how they can make the inferences needed to build CLDs using a standard digraph structure. Next, we develop a set of simple dynamic hypotheses and corresponding CLDs from leading SD textbooks. We then compare the four different combinations of prompting techniques, evaluating their performance against CLDs labeled by expert modelers. Results show that for simple model structures and using curated prompting techniques, LLMs can generate CLDs of a similar quality to expert-built ones, accelerating CLD creation.
Problem

Research questions and friction points this paper is trying to address.

Automating causal loop diagram generation from dynamic hypotheses
Overcoming challenges in extracting variables and relationships for novice modelers
Evaluating LLM performance in creating expert-quality CLDs with curated prompts
Innovation

Methods, ideas, or system contributions that make the work stand out.

Using LLMs for automated CLD generation
Curated prompting enhances CLD accuracy
LLMs match expert quality in CLDs