jevbench
GautamTalksDev/jevbench
Preregistered, bias-corrected test of TypeSafe Jev's calibration under human disagreement (ChaosNLI, 100 labels per item)
- Stars
- 1
- Forks
- 0
Why it is listed
An independent preregistered ChaosNLI study of whether Jev confidence falls when human annotators disagree. Included as empirical research, not proof of a calibration result.