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
Collections
1
models
3
datasets
8
kensho/NoFreeLabelsPairwise
Viewer
•
Updated
•
604
•
11
kensho/NoFreeLabels
Viewer
•
Updated
•
1.2k
•
9
kensho/CMTBench
Viewer
•
Updated
•
20
•
9
kensho/BFFBench
Viewer
•
Updated
•
80
•
10
kensho/DocFinQA
Viewer
•
Updated
•
7.44k
•
327
•
4
kensho/bizbench
Viewer
•
Updated
•
19.1k
•
347
•
3
kensho/spgispeech
Updated
•
422
•
24
kensho/spgispeech_demo
Updated
•
9
•
1