Human Preference Evaluation for Response Quality on KIDBench
56KIDLlama ScoreHuman Preference Evaluation
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Human Preference EvaluationAnnotator=Annotator 22026.05 | 56 | 34 | 0 | |
| Human Preference EvaluationAnnotator=Annotator 12026.05 | 53 | 27 | 10 | |
| Human Preference EvaluationAnnotator=Annotator 32026.05 | 53 | 37 | 0 |