利用大型语言模型实现因果回路图的自动生成：通过精选提示技术增强系统动力学建模
Leveraging Large Language Models for Automated Causal Loop Diagram Generation: Enhancing System Dynamics Modeling through Curated Prompting Techniques
- MGH Institute for Technology Assessment, Harvard Medical School（哈佛医学院MGH技术评估研究所）
- Melbourne Business School, University of Melbourne（墨尔本大学墨尔本商学院）
- Sloan School of Management, Massachusetts Institute of Technology（麻省理工学院斯隆管理学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出并测试了利用大型语言模型和精选提示技术自动将动态假设转化为因果回路图的方法，实验表明其生成质量可与专家构建的CLD相媲美，显著加速建模过程。
AI中文摘要：
将动态假设转化为因果回路图（CLD）对于系统动力学建模至关重要。对于新手建模者而言，从文本中提取关键变量和因果关系以构建CLD往往具有挑战性且耗时，这限制了系统动力学工具的采用。本文介绍并测试了一种利用大型语言模型（LLMs）结合精选提示技术，将动态假设自动转化为CLD的方法。我们首先描述了LLMs的工作原理以及它们如何利用标准有向图结构进行构建CLD所需的推理。接下来，我们从权威的系统动力学教科书中开发了一组简单的动态假设及相应的CLD。然后，我们比较了四种不同的提示技术组合，并根据专家建模者标注的CLD评估其性能。结果表明，对于简单的模型结构，使用精选提示技术，LLMs能够生成与专家构建的CLD质量相当的CLD，从而加速CLD的创建。
英文摘要：
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.
