大语言模型辅助交通管理计划编制：以WisDOT WisTMP系统为例
Large Language Model-Assisted Preparation of Transportation Management Plans: A Case Study with WisDOT WisTMP System
查看机构详情
- University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
- University of Wyoming（怀俄明大学）
- Purdue University（普渡大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本研究提出基于大语言模型（LLM）的框架，结合WisDOT WisTMP系统自动生成交通管理计划（TMP），经微调开源LLM可提升TMP生成效率，但存在过度生成策略等挑战。
中文摘要 AI 辅助
工作区是交通基础设施中至关重要却又危险的组成部分，需要精心设计交通管理计划（TMP）以保障安全与通行效率。然而，TMP的编制仍依赖从业者专业知识，劳动强度大。本文提出一种大语言模型（LLM）辅助框架，用于自动生成TMP内容，以WisDOT WisTMP系统为应用场景。该框架对多个不同规模的开源LLM进行微调并本地部署，以确保数据安全。为支持模型训练，我们从历史WisTMP文档构建了领域特定数据集，将PDF文件转换为JSON格式的结构化问答对。实验结果表明，微调在标准文本生成指标上显著提升性能；进一步的分部分和策略级分析显示，尽管LLM整体表现出色，但存在过度生成策略、难以生成项目特定理由及准确成本估算的问题，且从7B/8B规模扩展到14B时收益有限。这些发现证明了LLM提升TMP编制效率的潜力，同时也凸显了LLM辅助TMP开发的剩余挑战。源代码和演示视频将在该httpsURL公开。
英文摘要
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. 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. 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. 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 https://zihaosheng.github.io/TMP-LLM/.
