Large Language Model-Assisted Preparation of Transportation Management Plans: A Case Study with WisDOT WisTMP System

查看原文 / View Original 编辑 / Edit

Computer Science > Computation and Language arXiv:2610.10650 (cs) [Submitted on 7 Oct 2026] Title: Large Language Model-Assisted Preparation of Transportation Management Plans: A Case Study with WisDOT WisTMP System Authors: Zihao Sheng, Pei Li, Zilin Huang, Yen-Jung Chen, Yuhao Luo, Zhengyang Wan, Steven T. Parker, David A. Noyce, Sikai Chen.

计算机科学 > 计算与语言 arXiv:2610.10650 (cs) [2026年10月7日提交] 标题：大语言模型辅助交通管理计划编制：以威斯康星州交通部（WisDOT）WisTMP系统为例作者：Zihao Sheng, Pei Li, Zilin Huang, Yen-Jung Chen, Yuhao Luo, Zhengyang Wan, Steven T. Parker, David A. Noyce, Sikai Chen。

Abstract: Work zones are critical yet hazardous components of transportation infrastructure, requiring carefully designed Transportation Management Plans (TMPs) to ensure safety and mobility. However, TMP preparation remains labor-intensive and heavily dependent on practitioner expertise. This paper proposes a Large Language Model (LLM)-assisted framework to automate TMP content generation, leveraging the WisDOT WisTMP system as the application context.

摘要：施工区域是交通基础设施中关键但危险的组成部分，需要精心设计的交通管理计划（TMP）以确保安全和通行能力。然而，TMP的编制仍然是劳动密集型的，且高度依赖从业者的专业知识。本文提出了一种大语言模型（LLM）辅助框架，以实现TMP内容生成的自动化，并以威斯康星州交通部的WisTMP系统作为应用背景。

The framework fine-tunes multiple open-source LLMs across different model scales and deploys them locally to ensure data security. To support model training, we construct a domain-specific dataset from historical WisTMP documents by converting PDF files into structured question-answer pairs in JSON format.

该框架对多种不同规模的开源大语言模型进行了微调，并将其部署在本地以确保数据安全。为了支持模型训练，我们通过将PDF文件转换为JSON格式的结构化问答对，从历史WisTMP文档中构建了一个特定领域的数据集。

Experimental results show that fine-tuning significantly improves performance across standard text generation metrics. Further section-wise and strategy-level analyses reveal that, while LLMs achieve strong overall performance, they tend to over-generate strategies and struggle to produce project-specific justifications and accurate cost estimates.

实验结果表明，微调显著提高了模型在各项标准文本生成指标上的表现。进一步的分章节和策略层面的分析显示，尽管大语言模型在整体上表现出色，但它们倾向于过度生成策略，且在提供针对特定项目的理由和准确的成本估算方面存在困难。

In addition, scaling from 7B/8B to 14B yields limited gains. These findings demonstrate the potential of LLMs to improve TMP preparation efficiency while highlighting remaining challenges in LLM-assisted TMP development. The source code and demo videos will be publicly available at this https URL.

此外，将模型规模从7B/8B扩展到14B所带来的收益有限。这些发现展示了大语言模型在提高TMP编制效率方面的潜力，同时也突显了在大语言模型辅助TMP开发过程中尚存的挑战。源代码和演示视频将在该链接公开。