PyPI page
Author:
Hadi Mohammadi
Summary:
Estimate LLM-judge accuracy without gold labels and aggregate judge panels: Dawid-Skene EM, agreement statistics, bootstrap uncertainty
Latest version:
0.1.0
Required dependencies:
numpy
Optional dependencies:
build
|
mypy
|
pytest
|
ruff
|
twine
Downloads last day:
1
Downloads last week:
9
Downloads last month:
26
7-day smoothing