Text Classification on Emotion (accuracy)
91.4AccuracyFine-Tuned
Evaluation results
| Method | Links | |
|---|---|---|
| Fine-TunedBackbone=RoBERTa-large2025.12 | 91.4 | |
| Fine-TunedBackbone=all-MiniLM-L12-v2, Method (Evaluation Protocol)=Fine-Tuned2025.12 | 81.7 | |
| Linear ProbeBackbone=all-MiniLM-L12-v2, Method (Evaluation Protocol)=Linear Probe2025.12 | 66.8 | |
| Task MatrixBackbone=RoBERTa-large, best layer=(1,2,10)2025.12 | 66 | |
| Task MatrixBackbone=all-MiniLM-L12-v2, Method (Evaluation Protocol)=Task Matrix, Best Layer=L112025.12 | 63.5 | |
| Curate-Train-Refinek=8, parameters=110M2026.01 | 61.6 | |
| MICBackbone=TinyBERT 6L, Dimension=7682026.05 | 61.31 | |
| MICBackbone=BERT, Dimension=7682026.05 | 60.36 | |
| Linear ProbeBackbone=RoBERTa-large2025.12 | 58.9 | |
| Curate-Train-Refinek=2, parameters=110M2026.01 | 56.5 | |
| Curate-Train-Refinek=4, parameters=110M2026.01 | 56 | |
| ADAPET-Basek=8, parameters=117M2026.01 | 53.9 | |
| AncSetFitk=4, parameters=110M2026.01 | 53.2 | |
| GliClass 3.0k=0, parameters=151M2026.01 | 51.9 | |
| Curate-Train-Refinek=0, parameters=110M2026.01 | 50.9 | |
| AncSetFitk=8, parameters=110M2026.01 | 50.9 | |
| AncSetFitk=2, parameters=110M2026.01 | 49.1 | |
| ADAPET-Basek=4, parameters=117M2026.01 | 45 | |
| ADAPET-Basek=2, parameters=117M2026.01 | 34.5 | |
| MICBackbone=TinyBERT 6L, Dimension=162026.05 | 31.51 | |
| MICBackbone=BERT, Dimension=162026.05 | 29.66 | |
| Base w/ FT ClassifierBackbone=all-MiniLM-L12-v2, Method (Evaluation Protocol)=Base w/ FT Classifier2025.12 | 24.5 |