Multi-class Classification on Original (test)
73.4Accuracy (0-shot)Ours best
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Ours bestbackbone=instructor-large, configuration=-P4, N1,32024.03 | 73.4 | 87.2 | |
| Disable LLMbackbone=instructor-large, LLM-generated data=false2024.03 | 71.7 | 85.5 | |
| Disable LLMBackbone=instructor-base2024.03 | 69.5 | 85.3 | |
| Ours bestBackbone=instructor-base, Prompt Variant=-P4, N1,32024.03 | 69.3 | 86.4 | |
| Baselinebackbone=instructor-large2024.03 | 67.6 | 86.2 | |
| BaselineBackbone=instructor-base2024.03 | 67.5 | 85.8 |