Large Language Model-Assisted Preparation of Transportation Management Plans: A Case Study with WisDOT WisTMP System
Quick Answer
This study introduces a Large Language Model (LLM)-assisted framework for automating Transportation Management Plan (TMP) generation using the WisDOT WisTMP system.
Quick Take
Fine-tuning various open-source showed improved performance metrics, although challenges remain in project-specific justifications and cost estimates, with limited gains from scaling model sizes from 7B/8B to 14B parameters.
Key Points
- LLM framework automates TMP content generation, reducing labor intensity.
- Fine-tuning improved performance across standard text generation metrics.
- Challenges include over-generation of strategies and inaccurate cost estimates.
- Scaling from 7B/8B to 14B models yielded limited performance gains.
- Source code and demo videos will be publicly available.
DeepSignal Analysis
What happened
The study presents a framework utilizing Large Language Models (LLMs) to automate the generation of Transportation Management Plans (TMPs) within the WisDOT WisTMP system. The research involved fine-tuning various open-source LLMs, which resulted in improved performance metrics, although challenges in project-specific justifications and cost estimates persist.
Key evidence
- The framework employs multiple open-source LLMs, fine-tuning them to enhance performance in TMP content generation.
- A domain-specific dataset was created from historical WisTMP documents, converting PDF files into structured question-answer pairs in JSON format.
- Scaling model sizes from 7B/8B to 14B parameters yielded limited improvements in performance metrics.
Why it matters
This research highlights the potential of LLMs to streamline the labor-intensive process of TMP preparation, which is crucial for ensuring safety in work zones. However, the ongoing challenges in generating project-specific justifications and accurate cost estimates indicate that further advancements are necessary before widespread adoption can occur.
What to watch
Paper Resources
📖 Reader Mode
~2 min readAbstract: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 this https URL.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.10650 [cs.CL] |
| (or arXiv:2610.10650v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10650 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zihao Sheng [view email]
[v1]
Wed, 7 Oct 2026 15:51:01 UTC (1,682 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →The "10th Juror": Open-Set Standpoint Screening for Bureaucratic Bias Detection
MARS-Gov introduces a framework for detecting bureaucratic bias in Dutch government documents, achieving a new state-of-the-art F1 score of 0.880. This model outperforms existing zero-shot detectors by 20.2 points and reduces unnecessary interventions to just 2.5%. The framework's dynamic '10th juror' adapts to emerging biases, enhancing legal language processing.