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 19
kensho/frontierfinance
Viewer • Updated • 30 • 606
kensho/CMTBench
Viewer • Updated • 20 • 93
kensho/BFFBench
Viewer • Updated • 80 • 302
kensho/VERDICTS
Viewer • Updated • 3.6k • 372
kensho/VERDICTSPairwise
Viewer • Updated • 604 • 95
kensho/FIND
Viewer • Updated • 6.1k • 71
kensho/WILD-raw
Viewer • Updated • 7.24M • 2.42k • 3
kensho/WILD
Viewer • Updated • 7.35M • 2.24k • 2
kensho/SPGISpeech2.0
Viewer • Updated • 170k • 3.82k • 5
kensho/PubTables-v2
Viewer • Updated • 3M • 5.56k • 27