aceEffect of hierarchical prompt engineering on convolutional neural networks generated by large language models for helmet wearing compliance classification
Abstract Non-compliance with Personal Protective Equipment (PPE) use regulations, particularly helmet wearing, remains a critical occupational safety challenge in high-risk industrial environments. This study investigates how hierarchical prompt engineering shapes the quality of Convolutional Neural Networks (CNNs) generated by Large Language Models (LLMs) for image-level helmet-wearing compliance classification (helmet vs. no-helmet) as a mechanism for PPE compliance monitoring. Four LLMs (ChatGPT, Claude, Gemi…
Basic and structured prompts led four LLMs to generate working helmet-compliance classifiers that reached high accuracy on a controlled image test set.
Over-specified Tier 3 prompts caused Gemini and Grok to generate CNNs that failed to converge, so more detailed prompting is not reliably better.
Each LLM-tier condition is represented by a single generated script, the evaluation is controlled and image-level, and validation in real industrial settings is still required.
Evidence
- Peer-reviewedDiscover Artificial Intelligence2026-10-17
How should this claim be treated?
Truvace Impact Record TRV-2026-1850, v1: “Effect of hierarchical prompt engineering on convolutional neural networks generated by large language models for helmet wearing compliance classification.” Truvace, 2026-10-18. /record/TRV-2026-1850 (accessed at citation time). sha256 2d7f253d04e25751…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-1850 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.