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
11
kensho/FFQuantityExtraction
Viewer
•
Updated
•
223
•
34
•
1
kensho/FFProgramSynthesis
Viewer
•
Updated
•
246
•
54
•
1
kensho/FFDomainKnowledge
Viewer
•
Updated
•
131
•
45
•
3
kensho/NoFreeLabelsPairwise
Viewer
•
Updated
•
604
•
43
kensho/NoFreeLabels
Viewer
•
Updated
•
1.2k
•
41
kensho/CMTBench
Viewer
•
Updated
•
20
•
47
kensho/BFFBench
Viewer
•
Updated
•
80
•
53
kensho/DocFinQA
Viewer
•
Updated
•
7.44k
•
1.17k
•
12
kensho/bizbench
Viewer
•
Updated
•
19.1k
•
223
•
6
kensho/spgispeech
Updated
•
2.86k
•
33