Natural Language Inference on SNLI Original (test)
93.12AccuracyRoBERTa
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| RoBERTaMitigation Approach=None2026.04 | 93.12 | — | |
| AugmentationMitigation Approach=Augmentation, Base Model=ELECTRA-small2026.04 | 89.41 | — | |
| ELECTRA (Hybrid)Training Configuration=Hybrid, Evaluation Protocol=Fine-tuned2026.04 | 89.24 | 0.0008 | |
| Hybrid MitigationMitigation Approach=Hybrid, Base Model=ELECTRA-small2026.04 | 89.24 | — | |
| ELECTRA (Baseline)Training Configuration=Baseline, Evaluation Protocol=Fine-tuned2026.04 | 89.07 | 0.0036 | |
| ELECTRA-smallMitigation Approach=None2026.04 | 89.07 | — | |
| PreprocessingMitigation Approach=Preprocessing, Base Model=ELECTRA-small2026.04 | 89.05 | — | |
| GPT-4o-miniEvaluation Protocol=Zero-shot2026.04 | 87.9 | — | |
| GPT-4o-miniMitigation Approach=None2026.04 | 87.9 | — | |
| GPT-3.5Mitigation Approach=None2026.04 | 66.65 | — |