Collection of datasets for the paper "No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding"
Kensho
company
Verified
AI & ML interests
Research, develop and implement leading AI and machine learning capabilities that bring structure and insights to complex data.
Recent Activity
datasets 18
kensho/CMTBench
Viewer • Updated • 20 • 21
kensho/BFFBench
Viewer • Updated • 80 • 24
kensho/VERDICTS
Viewer • Updated • 3.6k • 12
kensho/VERDICTSPairwise
Viewer • Updated • 604 • 13
kensho/FIND
Viewer • Updated • 6.1k • 30
kensho/WILD-raw
Viewer • Updated • 7.24M • 938
kensho/WILD
Viewer • Updated • 7.35M • 279
kensho/SPGISpeech2.0
Viewer • Updated • 170k • 809 • 4
kensho/PubTables-v2
Viewer • Updated • 3M • 1.58k • 22
kensho/spgispeech
Viewer • Updated • 2.7M • 6.19k • 41