Bridge-RoadLM: Building a Domain-Adapted Large Language Model for Bridge Pavement Maintenance Based on Authoritative Specification Corpora and Efficient Parameter Fine-Tuning
Journal of Performance of Constructed Facilities · 01.02.2027 · 41 (1)
DOI: 10.1061/jpcfev.cfeng-5649 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Performance of Constructed Facilities, erschienen am 01.02.2027. Verfasst von Yutao Zhu und 4 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben.
Abstract (Originalsprache)
General large language models (LLMs) often have limited reliability when addressing specialized bridge pavement maintenance tasks. This study proposes Bridge-RoadLM, a domain-adapted framework for preliminary bridge pavement maintenance support. We developed an automated data engineering pipeline to construct the Bridge-Road Corpus, comprising 10,000 instruction-following samples derived from authoritative specifications and technical documents. Using parameter-efficient fine-tuning (PEFT/LoRA), representative Qwen, DeepSeek, LLaMA, and Gemma models were adapted to bridge pavement maintenance tasks. A multilevel evaluation framework was established, including automated linguistic metrics, a 500-question expert-validated test bank, and a blinded multiengineer evaluation of open-ended inspection-report-style cases. Results show improved controlled task performance for several fine-tuned models, and the strongest improvement was for Qwen3-8B. Its accuracy in pavement defect diagnosis increased from 45.0% to 81.0%, with 95% Wilson confidence intervals of 35.6%–54.8% and 72.2%–87.5%, respectively. Its accuracy in bridge monitoring and maintenance increased from 25.0% to 75.0%, with 95% Wilson confidence intervals of 17.5%–34.3% and 65.7%–82.5%, respectively. In the blinded open-ended evaluation, six engineers with 10–17 years of professional experience scored anonymized model outputs using five predefined criteria: correctness, completeness, traceability, hallucination control, and safety. Qwen3-8B achieved the highest average score among the nine evaluated models. The results also show that fine-tuning effects varied across model families, indicating that domain-specific PEFT does not uniformly improve all LLMs. Overall, this study provides a specification-based instruction corpus and a controlled evaluation workflow for adapting locally deployable LLMs to bridge pavement maintenance, supporting preliminary specification referencing, defect interpretation, and draft-level maintenance-plan preparation within a human-in-the-loop workflow.
Zitieren
APA
Zhu, Y., Wang, J., Zhang, L., Liu, Z., & Xu, Y. (2027). Bridge-RoadLM: Building a Domain-Adapted Large Language Model for Bridge Pavement Maintenance Based on Authoritative Specification Corpora and Efficient Parameter Fine-Tuning. Journal of Performance of Constructed Facilities, 41(1). https://doi.org/10.1061/jpcfev.cfeng-5649
Vancouver
Zhu Y, Wang J, Zhang L, Liu Z, Xu Y. Bridge-RoadLM: Building a Domain-Adapted Large Language Model for Bridge Pavement Maintenance Based on Authoritative Specification Corpora and Efficient Parameter Fine-Tuning. Journal of Performance of Constructed Facilities. 2027;41(1). doi:10.1061/jpcfev.cfeng-5649
BibTeX
@article{Zhu2027,
author = {Zhu, Yutao and Wang, Junjie and Zhang, Lijuan and Liu, Zhaoxu and Xu, Yun},
title = {Bridge-RoadLM: Building a Domain-Adapted Large Language Model for Bridge Pavement Maintenance Based on Authoritative Specification Corpora and Efficient Parameter Fine-Tuning},
journal = {Journal of Performance of Constructed Facilities},
year = {2027},
volume = {41},
number = {1},
doi = {10.1061/jpcfev.cfeng-5649}
}
EUVIMED