Identifying plausible explanations on δ-SNLI
81.6AccuracyRoBERTa
Evaluation results
| Method | Links | |
|---|---|---|
| RoBERTaplausibility annotations=with2023.05 | 81.6 | |
| KDDC-CSKG (N)knowledge-augmented=true, plausibility annotations=without2023.05 | 69.93 | |
| KDDC-ATOMIC (N)knowledge-augmented=true, plausibility annotations=without2023.05 | 69.83 | |
| LiPoRplausibility annotations=without2023.05 | 65.26 | |
| Tuned BARTsetting=tuned, plausibility annotations=without2023.05 | 64.76 | |
| KDDC-CWWV (N)knowledge-augmented=true, plausibility annotations=without2023.05 | 63.24 | |
| ZS BARTsetting=zero-shot, plausibility annotations=without2023.05 | 55.12 | |
| ZS GPT3setting=zero-shot, plausibility annotations=without2023.05 | 49.69 | |
| ZS GPT-NEOsetting=zero-shot, plausibility annotations=without2023.05 | 45.38 |