AI & MLCoreAIML-EVAL-007
Human Evaluation
Protocols, agreement, and cost: when only people can judge.
- Difficulty
- 2 / 5
- Importance
- 5 / 5
- Study time
- 1–2 h
- Kind of work
- Mixed
Why it matters
The learner can design a tiny pairwise-judgment protocol and state what agreement measures.