A RAND team turned a 64-paper literature review into a preliminary best-practice checklist for rigorously evaluating general-purpose AI models.
As of 10 October 2024: https://data.consilium.europa.eu/doc/document/ PE-24-2024-INIT/en/pdf Findley, Michael G., Kyosuke Kikuta & Michael Denly
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Preliminary suggestions for rigorous GPAI model evaluations
A RAND team turned a 64-paper literature review into a preliminary best-practice checklist for rigorously evaluating general-purpose AI models.