Structuring large language models for chemical health risk reasoning in environmental and occupational exposure

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Not quantified - described as 'consistent outperformance'

• Primary Outcome: LLM-RAG system outperformed baseline models in correctness, faithfulness, and domain-specific helpfulness

• Nnt Or Sensitivity: Performance metrics not quantified with specific values

• Confidence Interval: Not reported

Clinical Application

Requires technical infrastructure and validation before clinical deployment Relevant to Safe Work Australia guidelines, NOHSC exposure standards, and TGA chemical assessment processes Environmental health professionals, occupational hygienists, toxicologists, and regulatory assessors

Abstract

Large language models (LLMs) have revolutionized numerous scientific fields. However, their application in environmental health remains limited, as they are prone to hallucinations and struggle with reasoning over complex, real-world exposure data. Chemical risks, especially from rare or poorly studied compounds, span diverse occupational and everyday scenarios, where structured knowledge is often incomplete and poorly integrated. To address these challenges, we present a health risk assistant that integrates deep learning-based compound property prediction, retrieval-augmented generation (RAG), and prompt engineering into a unified reasoning framework. Central to our design are two synergistic strategies: semantic structuring, which reorganizes heterogeneous knowledge into context-consistent and semantically rich profiles, and domain-aware prompting, which guides large language models through structured and role-specific reasoning aligned with toxicological goals. The framework enables the system to map physicochemical attributes to exposure pathways and disease outcomes with improved relevance and fidelity. Evaluated on a 100-question benchmark spanning chronic toxicity, occupational hazards, and exposure-specific risks, our LLM-RAG system consistently outperforms baseline models in correctness, faithfulness, and domain-specific helpfulness. Beyond answering queries, our approach demonstrates how integrated knowledge curation and tailored prompting can enable trustworthy and scalable AI reasoning for public and environmental health protection.

References

1. 1.Chen, Z., Du, M., Qian, C., & Yu, H-Q. (2026). Structuring large language models for chemical health risk reasoning in environmental and occupational exposure. Journal of Hazardous Materials, 141820. https://doi.org/10.1016/j.jhazmat.2026.141820