Automated Hazard Identification and Risk Assessment in Occupational Health and Safety Using Artificial Intelligence Fine-Tuned Large Language Models

Mesut Çiçek; Aytaç Uğur Yerden

doi:10.35377/saucis...1870465

Automated Hazard Identification and Risk Assessment in Occupational Health and Safety Using Artificial Intelligence Fine-Tuned Large Language Models

Abstract

Occupational health and safety management requires systematic hazard identification and comprehensive risk assessment. Traditional approaches rely on manual processes that can be time-consuming and inconsistent across evaluators. In this study, we present an automated artificial intelligence system for hazard identification and risk assessment using fine-tuned large language models. We leverage Qwen3-32B as the base model. This model was adapted via Low-Rank Adaptation (LoRA), a parameter-efficient fine-tuning method, to acquire domain-specific knowledge of workplace hazards, risk assessment methodologies, and safety control measures. We trained our model on a dataset of hazard scenarios prepared by occupational safety experts. Each sample contains structured JSON outputs, including the hazard name, description, probability score, severity score, and control measures. Our evaluation on a held-out test set shows promising results. The fine-tuned model achieved an F1-score of 0.8830, which represents a 32.1\% improvement over the base model. We observed balanced precision (0.8826) and recall (0.8836), with an overall classification accuracy of 88.3\%. One particularly noteworthy finding is that no extreme misclassifications occurred between the high- and low-risk categories. This pattern indicates conservative and safety-conscious predictions. Our findings demonstrate that large language models can be effectively adapted to specialized occupational safety tasks through parameter-efficient fine-tuning. This approach offers significant potential as a decision support tool to enhance consistency and efficiency in safety management practices.

Keywords

Thanks

This research is part of the researcher's PhD studies at Istanbul Gedik University.

References

Kuok Ho Daniel Tang. Artificial intelligence in occupational health and safety risk management of construction, mining, and oil and gas sectors: advances and prospects. Journal of Engineering Research and Reports, 26(6):241–253, 2024.
Adel Badri, Bryan Boudreau-Trudel, and Ahmed Saâdeddine Souissi. Occupational health and safety in the industry 4.0 era: A cause for major concern? Safety Science, 109:403–411, 2018.
Immad A. Shah and SukhDev Mishra. Artificial intelligence in advancing occupational health and safety: an encapsulation of developments. Journal of Occupational Health, 66(1):uiad017, 2024.
Ran Liu, Hu-Chen Liu, Hua Shi, and Xiuzhu Gu. Occupational health and safety risk assessment: A systematic literature review of models, methods, and applications. Safety Science, 160:106050, 2023.
Jiyoung Park and Dongheon Kang. Artificial intelligence and smart technologies in safety management: a comprehensive analysis across multiple industries. Applied Sciences, 14(24):11934, 2024.
Likang Wu, Zhi Zheng, Zhaopeng Qiu, Hao Wang, Hongchao Gu, Tingjia Shen, Chuan Qin, Chen Zhu, Hengshu Zhu, Qi Liu, et al. A survey on large language models for recommendation. World Wide Web, 27(5):60, 2024.
Yogesh K. Dwivedi, Nir Kshetri, Laurie Hughes, Emma Louise Slade, Anand Jeyaraj, Arpan Kumar Kar, Abdullah M. Baabdullah, Alex Koohang, Vishnupriya Raghavan, Manju Ahuja, et al. Opinion paper: “So what if ChatGPT wrote it?” Multidisciplinary perspectives on opportunities, challenges and implications of generative conversational AI for research, practice and policy. International Journal of Information Management, 71:102642, 2023.
Jungwon Lee, Seungjun Ahn, Daeho Kim, and Dongkyun Kim. Performance comparison of retrieval-augmented generation and fine-tuned large language models for construction safety management knowledge retrieval. Automation in Construction, 168:105846, 2024.

Onur Doğan and Mustafa Özgür Keskin. L tipi matris yöntemi ve AHP yöntemi kullanılarak risklerin değerlendirilmesi: Örnek bir uygulama. Mühendislik Bilimleri ve Tasarım Dergisi, 11(4):1282–1293, 2023.
Onur Doğan, Pınar Bozbeyoğlu, and Nazım Erkoç. Evaluation of risks by L-type (5×5) matrix method in an ore concentration structure: A case study. International Journal of Innovative Approaches in Science Research, 7(3):75–90, 2023.
Nurettin Koç and Redvan Ghasemlounia. A new risk analysis method in the construction sector: HES. Journal of Architectural Sciences and Applications, 10(1):508–519, 2025.
Berna Gür, Şenol Yavuz, Ahmet Doğan Çakır, and Dursun Ali Köse. Determination of hazards and risks in a solar power plant using the matrix risk analysis. Avrupa Bilim ve Teknoloji Dergisi, (23):497–511, 2021.
Anıl Utku. Artificial intelligence-driven risk assessment in civil engineering projects: A comparative analysis of machine learning models. Erciyes Üniversitesi Fen Bilimleri Enstitüsü Fen Bilimleri Dergisi, 41(2):548–561, 2025.
Martin Westhoven. Requirements for AI support in occupational safety risk analysis. In Mensch und Computer 2022, pages 561–565, New York, NY, USA, September 2022. ACM.
Yang Jiao, Jintao Dong, Jingru Han, and Huabo Sun. Classification and causes identification of Chinese civil aviation incident reports. Applied Sciences, 12(21):10765, 2022.
Mason Smetana, Lucio Salles de Salles, Igor Sukharev, and Lev Khazanovich. Highway construction safety analysis using large language models. Applied Sciences, 14(4):1352, 2024.
Seungwon Baek, Chan Young Park, and Wooyong Jung. Automated safety risk management guidance enhanced by retrieval-augmented large language model. Automation in Construction, 176:106255, 2025.
Mario Luca Bernardi, Marta Cimitile, Giovanni Panella, Riccardo Pecori, and Giuditta Simoncelli. Automatic generation of job safety reports with explainable RAG-based LLMs. Information Systems Frontiers, pages 1–15, 2025.
Natalia Orviz-Martínez, Efrén Pérez-Santín, and José Ignacio López-Sánchez. New trends in the use of artificial intelligence and natural language processing to occupational risks prevention. 2025.
An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. Qwen3 technical report. arXiv preprint arXiv:2505.09388, 2025.
Padma Iyenghar. Empirical evaluation of reasoning LLMs in machinery functional safety risk assessment and the limits of anthropomorphized reasoning. Electronics, 14(18):3624, 2025.
Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. LoRA: Low-rank adaptation of large language models. ICLR, 1(2):3, 2022.
Yuren Mao, Yuhang Ge, Yijiang Fan, Wenyi Xu, Yu Mi, Zhonghao Hu, and Yunjun Gao. A survey on LoRA of large language models. Frontiers of Computer Science, 19(7):197605, 2025.
Hyesung Jeon, Yulhwa Kim, and Jae-Joon Kim. L4Q: Parameter efficient quantization-aware fine-tuning on large language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2002–2024, 2025.
David M. W. Powers. Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv preprint arXiv:2010.16061, 2020.

Details

Primary Language

English

Subjects

Natural Language Processing

Journal Section

Research Article

Authors

Mesut Çiçek
0000-0001-7874-5852
Türkiye

Aytaç Uğur Yerden ^*
0000-0002-3886-802X
Türkiye

Early Pub Date

June 22, 2026

Publication Date

June 30, 2026

Submission Date

January 23, 2026

Acceptance Date

February 9, 2026

Published in Issue

Year 2026 Volume: 9 Number: 3

DOI

https://doi.org/10.35377/saucis...1870465

IZ

https://izlik.org/JA27RZ42TW

Cite

RIS / Bibtex

APA

Çiçek, M., & Yerden, A. U. (2026). Automated Hazard Identification and Risk Assessment in Occupational Health and Safety Using Artificial Intelligence Fine-Tuned Large Language Models. Sakarya University Journal of Computer and Information Sciences, 9(3), 765-774. https://doi.org/10.35377/saucis...1870465

AMA

1.Çiçek M, Yerden AU. Automated Hazard Identification and Risk Assessment in Occupational Health and Safety Using Artificial Intelligence Fine-Tuned Large Language Models. SAUCIS. 2026;9(3):765-774. doi:10.35377/saucis.1870465

Chicago

Çiçek, Mesut, and Aytaç Uğur Yerden. 2026. “Automated Hazard Identification and Risk Assessment in Occupational Health and Safety Using Artificial Intelligence Fine-Tuned Large Language Models”. Sakarya University Journal of Computer and Information Sciences 9 (3): 765-74. https://doi.org/10.35377/saucis. 1870465.

EndNote

Çiçek M, Yerden AU (June 1, 2026) Automated Hazard Identification and Risk Assessment in Occupational Health and Safety Using Artificial Intelligence Fine-Tuned Large Language Models. Sakarya University Journal of Computer and Information Sciences 9 3 765–774.

IEEE

[1]M. Çiçek and A. U. Yerden, “Automated Hazard Identification and Risk Assessment in Occupational Health and Safety Using Artificial Intelligence Fine-Tuned Large Language Models”, SAUCIS, vol. 9, no. 3, pp. 765–774, June 2026, doi: 10.35377/saucis...1870465.

ISNAD

Çiçek, Mesut - Yerden, Aytaç Uğur. “Automated Hazard Identification and Risk Assessment in Occupational Health and Safety Using Artificial Intelligence Fine-Tuned Large Language Models”. Sakarya University Journal of Computer and Information Sciences 9/3 (June 1, 2026): 765-774. https://doi.org/10.35377/saucis. 1870465.

JAMA

1.Çiçek M, Yerden AU. Automated Hazard Identification and Risk Assessment in Occupational Health and Safety Using Artificial Intelligence Fine-Tuned Large Language Models. SAUCIS. 2026;9:765–774.

MLA

Çiçek, Mesut, and Aytaç Uğur Yerden. “Automated Hazard Identification and Risk Assessment in Occupational Health and Safety Using Artificial Intelligence Fine-Tuned Large Language Models”. Sakarya University Journal of Computer and Information Sciences, vol. 9, no. 3, June 2026, pp. 765-74, doi:10.35377/saucis. 1870465.

Vancouver

1.Mesut Çiçek, Aytaç Uğur Yerden. Automated Hazard Identification and Risk Assessment in Occupational Health and Safety Using Artificial Intelligence Fine-Tuned Large Language Models. SAUCIS. 2026 Jun. 1;9(3):765-74. doi:10.35377/saucis. 1870465