User Satisfaction Evaluation on Follow-up Study (Proficient)
3.91Mean Satisfaction RatingExPerT
Evaluation results
| Method | Links | |
|---|---|---|
| ExPerTBackbone=gpt-5.3-chat-latest, Expertise Conditioning Protocol=Predicted2026.05 | 3.91 | |
| Self-Reported Expertise ConditioningBackbone=gpt-5.3-chat-latest, Expertise Conditioning Protocol=Self-Reported2026.05 | 3.89 | |
| Without Expertise ConditioningBackbone=gpt-5.3-chat-latest, Expertise Conditioning Protocol=None2026.05 | 3.57 |