Review
Open access
Aug 2026
Evaluating LLMs for Automated Extraction and Classification of Science, Technology and Innovation (STI) Indicators
The results show that current LLMs are not reliable for unsupervised STI indicator workflows, and Hybrid human-AI approaches are recommended as a near-term alternative.
Camila Nunes, Pablo Sampaioa, Kellyton Britoa
· EGOV-CeDEM-ePart 2026 · 0 citations