Toward a Theory of Evaluability
Imported from official source
Machine learning models, particularly large foundation models, are increasingly evaluated along multiple axes that are relevant for their usage. In addition to accuracy measures appropriate for the specific task of interest, measures capturing safety, calibration and fairness properties are often of interest. …
This version
- Version
- 1 of 1
- Recorded
- November 16, 2026 19:02
- Change
- Initial
- Content hash
eb3f85fdb3b454c6f035c911de234f60- All versions
- Revision history