Naming the Hazard Category, Missing the Accident Mechanism: Fatal-Accident Coverage of LLM-Drafted Construction Risk Assessments Generated from Work Names Alone
Buildings · 16.11.2026 · 16 (22) · 4554
DOI: 10.3390/buildings16224554 ↗Kurz gefasst
Fachartikel in der Zeitschrift Buildings, online erschienen am 16.11.2026. Verfasst von Jongho Lee und 2 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Land, Infrastructure and Transport.
Abstract (Originalsprache)
Large language models (LLMs) can draft construction risk assessments from work names, but their coverage of fatal-accident mechanisms is uncertain. We evaluated 2097 hazards generated by GPT-5.6 Sol and Claude Fable 5 from work-category, work, and unit-work names alone. The reference was 1687 hazard factors for 113 unit works from the Korea Occupational Safety and Health Agency’s fatality-derived table (2016–2021). Two LLM judges scored hazard coverage and control adequacy. Two external experts independently rated 198 sampled items (judge–expert quadratic-weighted κ = 0.65–0.84). At the boundary between no and partial coverage, unweighted κ was only 0.37–0.71. Across the four service–judge combinations, 66.9–77.2% of the reference hazard factors were at least partially covered, but only 25.5–29.0% were fully covered. Full coverage is the primary and more reliable result, and it changed little under alternative matching rules. Shared omissions involved equipment states, work stages, and worker positions. Key preventive measures accompanied 95–97% of fully covered reference–draft pairs but 52–75% of partially covered pairs, depending on the judge; part of this association is built into the rubric. Of 5542 legal citations, 4689 cited the Rules on Occupational Safety and Health Standards; 99.6% of these named an existing article, and formal number–title agreement was 94.6% (GPT-5.6 Sol) and 95.9% (Claude Fable 5). All estimates describe one generation per service under the tested conditions and should not be generalized to the models’ overall performance. Such drafts require review focused on specific accident conditions and controls.
Förderung
- Ministry of Land, Infrastructure and Transport
Zitieren
APA
Lee, J., Lee, Y., & Lee, J. (2026). Naming the Hazard Category, Missing the Accident Mechanism: Fatal-Accident Coverage of LLM-Drafted Construction Risk Assessments Generated from Work Names Alone. Buildings, 16(22), 4554. https://doi.org/10.3390/buildings16224554
Vancouver
Lee J, Lee Y, Lee J. Naming the Hazard Category, Missing the Accident Mechanism: Fatal-Accident Coverage of LLM-Drafted Construction Risk Assessments Generated from Work Names Alone. Buildings. 2026;16(22):4554. doi:10.3390/buildings16224554
BibTeX
@article{Lee2026,
author = {Lee, Jongho and Lee, Yongha and Lee, Jaewook},
title = {Naming the Hazard Category, Missing the Accident Mechanism: Fatal-Accident Coverage of LLM-Drafted Construction Risk Assessments Generated from Work Names Alone},
journal = {Buildings},
year = {2026},
volume = {16},
number = {22},
pages = {4554},
doi = {10.3390/buildings16224554}
}
EUVIMED