Text-based LLM extraction from Safety Data Sheets reaches at most 84% accuracy across four models and three prompting strategies, falling short of the 90% threshold for unsupervised industrial deployment.
Scientific Reports (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Benchmarking Large Language Models for Safety Data Extraction
Text-based LLM extraction from Safety Data Sheets reaches at most 84% accuracy across four models and three prompting strategies, falling short of the 90% threshold for unsupervised industrial deployment.