Enhancing Job Hazard Analysis Knowledge Retrieval Through Knowledge Graphs and Large Language Models
Bibliographic record
Abstract
Job Hazard Analysis (JHA) is a crucial process for identifying and mitigating risks in construction workplaces.Traditional JHA methods rely heavily on manual expertise, making them timeconsuming, knowledge-intensive, and prone to inconsistencies.This research proposes an AI-driven framework that integrates Large Language Models (LLMs) with Neo4j-based Knowledge Graphs (KGs) to enhance JHA workflows by automating hazard identification and mitigation planning.The framework extracts safety-related knowledge from Occupational Safety and Health Administration (OSHA) standards, structuring it into an intelligent KG for efficient hazard retrieval and analysis.By leveraging LLMs for entity recognition and relationship extraction, the system enables automated hazard identification, risk assessment, and regulatory compliance verification.A case study on OSHA lead exposure monitoring compliance illustrates how this approach structures safety regulations and generates actionable hazard insights.Future research will focus on improving the precision of LLM-driven hazard identification, optimizing scalability for large datasets, and conducting user validation studies to refine real-world applicability.The proposed solution bridges traditional knowledge management systems with LLM-driven automation, offering a scalable, cost-effective, and adaptable tool for improving workplace safety in the construction industry.
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 | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.005 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.005 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".