Social Norm Dialogue Generation on Prosocial-Dialog Korean
68Human PreferenceV2R
Evaluation results
| Method | Links | |
|---|---|---|
| V2REvaluation condition=Blind, Annotators=Native speakers, Base model=GPT-4o-mini2025.09 | 68 | |
| Untuned GPT-4o-miniEvaluation condition=Blind, Annotators=Native speakers2025.09 | 32 |