{"slug": "large-language-model-assisted-preparation-of-transportation-management-plans-a", "title": "Large Language Model-Assisted Preparation of Transportation Management Plans: A Case Study with WisDOT WisTMP System", "summary": "A new arXiv paper proposes an LLM-assisted framework that fine-tunes multiple open-source large language models, deployed locally for data security, to automate Transportation Management Plan content generation for the Wisconsin Department of Transportation's WisTMP system. The researchers built a domain-specific dataset by converting historical WisTMP PDFs into structured JSON question-answer pairs, and found fine-tuning significantly improved standard text generation metrics, though the models over-generate strategies and struggle with project-specific justifications and accurate cost estimates. Scaling from 7B/8B to 14B parameters yielded limited gains, and the source code and demo videos will be released at https://zihaosheng.github.io/TMP-LLM/.", "body_md": "arXiv:2610.10650v1 Announce Type: new \nAbstract: 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/.", "url": "https://wpnews.pro/news/large-language-model-assisted-preparation-of-transportation-management-plans-a", "canonical_source": "https://arxiv.org/abs/2610.10650", "published_at": "2026-10-09 04:00:00+00:00", "updated_at": "2026-10-09 04:17:45.634315+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "ai-research", "natural-language-processing"], "entities": ["Wisconsin Department of Transportation", "WisTMP", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/large-language-model-assisted-preparation-of-transportation-management-plans-a", "markdown": "https://wpnews.pro/news/large-language-model-assisted-preparation-of-transportation-management-plans-a.md", "text": "https://wpnews.pro/news/large-language-model-assisted-preparation-of-transportation-management-plans-a.txt", "jsonld": "https://wpnews.pro/news/large-language-model-assisted-preparation-of-transportation-management-plans-a.jsonld"}}