arXiv 2603.170212026-03-19cs.AI

生成AI辅助的参与建模在深不确定性下的社会环境规划

Generative AI-assisted Participatory Modeling in Socio-Environmental Planning under Deep Uncertainty

School of Computing（计算学院）；Information Systems, Faculty of Engineering（信息学院，工程学院）；Information Technology, The University of Melbourne, Parkville VIC 3010, Australia（信息科技，墨尔本大学，帕克维尔 VIC 3010, 澳大利亚）；Industrial Research Organization (CSIRO), Research Way, Clayton VIC 3168, Australia（工业研究组织（CSIRO），Research Way，克莱顿 VIC 3168, 澳大利亚）；Department of Psychiatry, The University of Melbourne, Parkville VIC 3010, Australia（精神病学系，墨尔本大学，帕克维尔 VIC 3010, 澳大利亚）

Zhihao Pei, Nir Lipovetzky, Angela M. Rojas-Arevalo, Fjalar J. de Haan, Enayat A. Moallemi

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出利用大语言模型简化社会环境规划中深不确定性下的问题概念化过程，通过模板化工作流实现参与建模，提升建模效率与准确性。

摘要：

在深不确定性下，社会环境规划需要研究人员在探索政策和部署计划之前识别和概念化问题。在实践中，这一问题概念化过程通常依赖参与建模将利益相关者的自然语言描述转化为定量模型，这一过程复杂且耗时。为此，我们提出了一种模板化的工作流，利用大语言模型进行初步的概念化过程。在工作流中，研究人员可以使用大语言模型从利益相关者的直观问题描述中识别出模型的核心组件，探索其多样的问题视角，将这些组件组装成统一的模型，并最终通过迭代沟通在Python中实现该模型。这些结果将促进后续的社会环境规划在深不确定性下的步骤。使用ChatGPT 5.2 Instant，我们在湖泊问题和电力市场问题上展示了这一工作流，两者均展示了社会环境规划问题。在两种情况下，经过几次迭代并经过人类验证和细化后获得了可接受的输出。这些实验表明，大语言模型可以作为有效工具，帮助在社会环境规划的问题概念化过程中进行参与建模。

英文摘要：

Socio-environmental planning under deep uncertainty requires researchers to identify and conceptualize problems before exploring policies and deploying plans. In practice and model-based planning approaches, this problem conceptualization process often relies on participatory modeling to translate stakeholders' natural-language descriptions into a quantitative model, making this process complex and time-consuming. To facilitate this process, we propose a templated workflow that uses large language models for an initial conceptualization process. During the workflow, researchers can use large language models to identify the essential model components from stakeholders' intuitive problem descriptions, explore their diverse perspectives approaching the problem, assemble these components into a unified model, and eventually implement the model in Python through iterative communication. These results will facilitate the subsequent socio-environmental planning under deep uncertainty steps. Using ChatGPT 5.2 Instant, we demonstrated this workflow on the lake problem and an electricity market problem, both of which demonstrate socio-environmental planning problems. In both cases, acceptable outputs were obtained after a few iterations with human verification and refinement. These experiments indicated that large language models can serve as an effective tool for facilitating participatory modeling in the problem conceptualization process in socio-environmental planning.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。