Introducing Evaluation Cards: A Live Interpretive Layer for Understanding the AI Evaluations Ecosystem
• 1
AI & ML interests
We’re building a research coalition on evaluating evaluations (EvalEval)! Hosted by Hugging Face, University of Edinburgh, and EleutherAI.
Recent Activity
View all activity
Articles
evaleval/entity-registry-data
Viewer • Updated • 229k • 642 • 1
evaleval/card_backend
Preview • Updated • 2.12k • 1
evaleval/EEE_datastore
Viewer • Updated • 4.99k • 24.6k • 32
evaleval/HELM_datastore
Updated • 36
evaleval/auto-benchmarkcards
Updated • 275 • 3
evaleval/EEE_datastore-flat-temp
Updated • 8.6k
evaleval/alphaxiv_datastore
Updated • 25 • 1
evaleval/social_impact_eval_annotations
Viewer • Updated • 4.24k • 18 • 4
evaleval/old_eee
Preview • Updated • 31