UDTR Global Radar

UDTR Global Rights of Nature Radar

Documentary registry of records detected across the scholarly, legal and institutional infrastructures monitored by UDTR.

A global documentary infrastructure designed to achieve the broadest verifiable and scientifically defensible coverage of the Rights of Nature.

← Back to Radar

Classifying construction accident reports with parameter-efficient fine-tuned LLMs and ensemble methods

Identification

Public canonical key
radar:r-54223a14229c44e7bcec150cced6ee79
Authors
Jun Wang · Jing Li · Shujie Wu · Ziyi Qu · Martin Skitmore · Nicholas Chileshe · Leyuan Ma
Reported year
2026
Reported language
en
Source type
article
First detected
2026-11-14T02:38:35.746162+00:00
Last metadata observation
2026-11-14T02:38:35.746162+00:00
Last HTTP verification
Not checked

Institutions reported by the source

Qingdao University of Technology · Bond University · Adelaide University · The University of Adelaide

Reported affiliation countries

AU · CN

Documentary abstract — original language

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.

Identifiers

OPENALEX
https://openalex.org/W7160427367
DOI
10.1108/ecam-12-2025-2035

Documentary context

Documentary family
article
Source-reported types
article
Publishers
Emerald Publishing Limited

Entity mentions are not evidence of legal recognition. Jurisdiction studied is separate from author affiliation country.

Sources

OpenAlex · Record 1

Cite this reference

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: bibliographic formats using available fields. OSCOLA / Bluebook: structured data only; full legal citation compliance is not claimed without verification of required elements.

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 Global Rights of Nature Legal Library. Classifying construction accident reports with parameter-efficient fine-tuned LLMs and ensemble methods. Documentary record: https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-54223a14229c44e7bcec150cced6ee79/ · Last HTTP verification: not performed

Report a correction

Frozen-version metadata

Research dossiers and documentary relations

Source roles

Bibliographic / original publication source · https://doi.org/10.1108/ecam-12-2025-2035

An authority link alone does not verify a legal claim. Abstracts and full texts remain subject to their source terms.

Documentary status

Relevance pending

Library

This identity is not yet included in the Legal Library.

UDTR Global Rights of Nature Legal Library