Demo ↗
MP4 · 11.2 MB
SI² — SuperIntelligence for Science
ChemSafe / SafeChem
Chemical hazard assessment and evaluation: hybrid retrieval-augmented decision support and safety benchmarking.
Research question
How can hybrid retrieval support laboratory chemical hazard assessment?
Research approach
This project brings together chemical hazard decision support and evaluation. ChemSafe studies hybrid retrieval-augmented laboratory hazard assessment; SafeChem introduces a benchmark for multi-label chemical hazard prediction and LLM safety hallucination evaluation.
Research outputs & focus
- Chemical hazard assessment and decision support
- Multi-label chemical hazard benchmarking
- LLM safety hallucination evaluation
People behind the project
Contributors.
Related publications
The research behind the tool.
ChemSafe: Hybrid Retrieval-Augmented Decision Support for Laboratory Chemical Hazard Assessment
Citation
Ran Elgedawy et al. (2026). ChemSafe: Hybrid Retrieval-Augmented Decision Support for Laboratory Chemical Hazard Assessment. JCDL.
SafeChem: A Benchmark Dataset for Multi-Label Chemical Hazard Prediction and LLM Safety Hallucination Evaluation
Submitted to NeurIPS
Citation
Ran Elgedawy et al. (2026). SafeChem: A Benchmark Dataset for Multi-Label Chemical Hazard Prediction and LLM Safety Hallucination Evaluation. ChemRxiv.