Integrating knowledge management and large language models to advance construction Job Hazard Analysis: A systematic review and conceptual framework
Bibliographic record
Abstract
Conducting a Job Hazard Analysis (JHA) remains essential for managing safety risks in construction; however, the process is often manual, subjective, and knowledge-intensive. While numerous studies have proposed tools and techniques to enhance JHA, a comprehensive synthesis through the lens of construction safety knowledge management (CSKM) has been lacking. This systematic review fills that gap by: (1) critically examining recent advancements in JHA practices with a focus on how tacit and explicit safety knowledge is acquired, integrated, and applied; (2) analyzing the emerging role of interoperable and semantic technologies – such as Building Information Modeling (BIM), ontologies, knowledge graphs (KGs), and semantic reasoning – in supporting JHA through CSKM; and (3) proposing a novel conceptual framework that outlines the potential integration of Large Language Models (LLMs) to automate and enhance JHA processes. Using the PRISMA methodology, 90 peer-reviewed studies were systematically reviewed and thematically analyzed. The results reveal actionable patterns in how digital technologies and knowledge management strategies are converging to address longstanding issues in hazard identification and decision-making. By embedding institutional knowledge into LLM-supported CSKM, this review contributes to the development of safer, more adaptive, and ultimately more sustainable construction practices.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.019 | 0.057 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.005 | 0.005 |
| Bibliometrics | 0.026 | 0.020 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.005 | 0.007 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".