Classifying construction accident reports with parameter-efficient fine-tuned LLMs and ensemble methods
Identification
- Clé publique
- radar:r-54223a14229c44e7bcec150cced6ee79
- Auteurs
- Jun Wang · Jing Li · Shujie Wu · Ziyi Qu · Martin Skitmore · Nicholas Chileshe · Leyuan Ma
- Année déclarée
- 2026
- Langue déclarée
- en
- Type source
- article
- Première détection
- 2026-11-14T02:38:35.746162+00:00
- Dernière observation des métadonnées
- 2026-11-14T02:38:35.746162+00:00
- Dernière vérification HTTP
- Non effectuée
Institutions déclarées par la source
Qingdao University of Technology · Bond University · Adelaide University · The University of Adelaide
Pays d’affiliation déclarés
AU · CN
Résumé documentaire — langue originale
Purpose The automated classification of construction accident reports is often inundated with persistent challenges such as low accuracy, data scarcity, class imbalance, and inadequate semantic representation. Therefore, to overcome those challenges, this study aims to develop a resource-efficient, high-performing ensemble framework that enhances safety information management, enables timely risk identification, and supports data-driven decision-making in construction safety. Design/methodology/approach A construction accident report dataset was processed using random oversampling to address severe class imbalance. Four large language models (DeBERTa-v3-Large, T5-Large, OPT, and Ettin-Encoder-1B) were adapted through parameter-efficient fine-tuning (PEFT) using the Low-Rank Adaptation (LoRA) method. Individual model predictions were aggregated via three ensemble techniques: hard voting, soft voting, and stacking, with stacking selected as the final integration strategy. The proposed ensemble framework was benchmarked against the performance of the individual fine-tuned models and three conventional baseline classifiers. Findings The ensemble models based on hard voting and stacking achieved the highest macro-average F1 score of 0.9377, surpassing all soft voting configurations as well as every individual LLM. In particular, the hard voting ensemble combining OPT, Ettin-Encoder-1B, and T5-Large and the stacking model using OPT and T5-Large demonstrated superior and stable performance across most accident subcategories. Both ensembles significantly outperformed single-model baselines, especially in the accurate identification of minority classes. Random oversampling effectively reduced class imbalance, while parameter-efficient fine-tuning maintained strong performance despite limited computational resources. Originality/value This study presents a novel integration of parameter-efficient fine-tuned large language models with ensemble learning for construction accident report classification. It introduces an effective, resource-efficient methodology that simultaneously tackles data imbalance and semantic complexity in safety-related text analysis. The framework offers practical value by enabling accurate, automated analysis of accident reports, reducing dependence on labor-intensive manual coding, and facilitating proactive safety management, hazard mitigation, and regulatory compliance in the construction industry.
Identifiants
- OPENALEX
- https://openalex.org/W7160427367
- DOI
- 10.1108/ecam-12-2025-2035
Repères documentaires
- Famille documentaire
- article
- Types déclarés par les sources
- article
- Éditeurs
- Emerald Publishing Limited
Les mentions d’entités ne constituent pas une preuve de reconnaissance juridique. La juridiction étudiée est distincte du pays d’affiliation des auteurs.
Sources
OpenAlex · Document 1
Citer cette référence
Jun Wang; Jing Li; Shujie Wu; Ziyi Qu; Martin Skitmore; Nicholas Chileshe; Leyuan Ma. Classifying construction accident reports with parameter-efficient fine-tuned LLMs and ensemble methods. 2026. https://doi.org/10.1108/ecam-12-2025-2035
JSON · CSL-JSON · BibTeX · RIS · CSV · JSON-LD ·
APA, Chicago, ISO 690 : formats bibliographiques fondés sur les champs disponibles. OSCOLA / Bluebook : données structurées uniquement ; aucune conformité juridique complète n’est revendiquée sans vérification des éléments nécessaires.
- APA
- Jun Wang; Jing Li; Shujie Wu; Ziyi Qu; Martin Skitmore; Nicholas Chileshe; Leyuan Ma. (2026). Classifying construction accident reports with parameter-efficient fine-tuned LLMs and ensemble methods. https://doi.org/10.1108/ecam-12-2025-2035
- Chicago
- Jun Wang; Jing Li; Shujie Wu; Ziyi Qu; Martin Skitmore; Nicholas Chileshe; Leyuan Ma. Classifying construction accident reports with parameter-efficient fine-tuned LLMs and ensemble methods. 2026. https://doi.org/10.1108/ecam-12-2025-2035
- ISO 690
- Jun Wang; Jing Li; Shujie Wu; Ziyi Qu; Martin Skitmore; Nicholas Chileshe; Leyuan Ma. Classifying construction accident reports with parameter-efficient fine-tuned LLMs and ensemble methods. 2026. https://doi.org/10.1108/ecam-12-2025-2035
Warning: Undefined array key "last_link_verified" in /home/clients/e27d81e12f04d2bfd747aa264540ac56/sites/_UDTR_APP/legal_library_reference.php on line 31
UDTR — Bibliothèque juridique mondiale des droits de la Nature. Classifying construction accident reports with parameter-efficient fine-tuned LLMs and ensemble methods. Notice documentaire: https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-54223a14229c44e7bcec150cced6ee79/ · Dernière vérification HTTP : non effectuée
Données de cette version figée
Dossiers et relations documentaires
Rôles des sources
Source bibliographique / publication d’origine · https://doi.org/10.1108/ecam-12-2025-2035
Un lien vers une autorité ne prouve pas à lui seul une affirmation juridique. Les résumés et les textes intégraux restent soumis aux conditions de leur source.
Statut documentaire
Pertinence à examiner
Bibliothèque
Cette identité n’est pas encore intégrée à la Bibliothèque juridique.