Question Classification on Trec-6
95.1AccuracyFine-Tuned
Evaluation results
| Method | Links | |
|---|---|---|
| Fine-TunedBackbone=RoBERTa-large2025.12 | 95.1 | |
| Fine-TunedBackbone=all-MiniLM-L12-v2, Method (Evaluation Protocol)=Fine-Tuned2025.12 | 93.2 | |
| Task MatrixBackbone=RoBERTa-large, best layer=(11)2025.12 | 84.9 | |
| Task MatrixBackbone=all-MiniLM-L12-v2, Method (Evaluation Protocol)=Task Matrix, Best Layer=L0,52025.12 | 84.7 | |
| Linear ProbeBackbone=RoBERTa-large2025.12 | 79.8 | |
| Linear ProbeBackbone=all-MiniLM-L12-v2, Method (Evaluation Protocol)=Linear Probe2025.12 | 75.1 | |
| Base w/ FT ClassifierBackbone=all-MiniLM-L12-v2, Method (Evaluation Protocol)=Base w/ FT Classifier2025.12 | 22.5 |