Multi-class Classification on Intent Semantic Toolkit (test)
33.9Accuracy (0-shot)Ours best
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Ours bestbackbone=instructor-large, configuration=-P4, N1,32024.03 | 33.9 | 37.2 | |
| Disable LLMbackbone=instructor-large, LLM-generated data=false2024.03 | 31.7 | 34.3 | |
| Baselinebackbone=instructor-large2024.03 | 29.2 | 34.1 | |
| Ours bestBackbone=instructor-base, Prompt Variant=-P4, N1,32024.03 | 28.3 | 33.8 | |
| Disable LLMBackbone=instructor-base2024.03 | 27 | 31.7 | |
| BaselineBackbone=instructor-base2024.03 | 26.4 | 31.1 |