Question Answering on Counterfacts
77.6EMCOIECD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| COIECDModel=FLAN-T5-3B2024.02 | 77.6 | 78.97 | |
| CDModel=FLAN-T5-3B2024.02 | 74.76 | 77.3 | |
| SCModel=FLAN-T5-3B2024.02 | 74.58 | 75.64 | |
| RegularModel=FLAN-T5-3B2024.02 | 74.56 | 75.73 | |
| CADModel=LLaMA2-13B2024.02 | 68.76 | 71.2 | |
| COIECDModel=LLaMA2-13B2024.02 | 68.3 | 69.33 | |
| CADModel=FLAN-T5-3B2024.02 | 68.23 | 74.17 | |
| CDModel=LLaMA2-13B2024.02 | 67.96 | 69.16 | |
| SCModel=LLaMA2-13B2024.02 | 61.76 | 62.76 | |
| RegularModel=LLaMA2-13B2024.02 | 61.67 | 62.63 | |
| CADModel=OPT-6.7B2024.02 | 40.1 | 40.31 | |
| CDModel=OPT-6.7B2024.02 | 38.16 | 37.9 | |
| COIECDModel=OPT-6.7B2024.02 | 37.35 | 40.47 | |
| SCModel=OPT-6.7B2024.02 | 21.4 | 24.24 | |
| RegularModel=OPT-6.7B2024.02 | 18.15 | 19.74 |