general family · filed under evaluation
Human evaluation
Evaluates models through human assessment, as distinct from automated evaluation.
Also called human evaluations.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
A range of automated as well as human evaluations were conducted to help improve model safety.
usedevaluation onlyin Gemma 4Google DeepMind
Filed alongside
Other methods under evaluation :: human & real-world evaluation.
Blind side-by-side expert evaluationMulti-turn open-ended external red-teamingInternal engineering task evaluationA/B testing on real tasksAutomated red-teaming loopContinuous monitoringCyber range exercisesDangerous-capability uplift assessmentExternal expert review of safety evaluation methodologyHeld-out evaluationPairwise comparison for Chinese writingPre-release safety evaluationReal-world codebase testingReal-world feedback refinementReward hacking mitigation in evaluationsSame-prompt comparative DevOps testingSystematic robustness-boundary characterizationWhite-collar enterprise task evaluation