Multiple-choice tasks on Natural Questions
59.6AccuracyTruthX
Evaluation Results
| Method | Links | |
|---|---|---|
| TruthXBackbone=Llama-2-7B-Chat2024.02 | 59.6 | |
| ITIBackbone=Llama-2-7B-Chat2024.02 | 57.83 | |
| Llama-2-7B-ChatBackbone=Llama-2-7B-Chat2024.02 | 54.9 |
| Method | Links | |
|---|---|---|
| TruthXBackbone=Llama-2-7B-Chat2024.02 | 59.6 | |
| ITIBackbone=Llama-2-7B-Chat2024.02 | 57.83 | |
| Llama-2-7B-ChatBackbone=Llama-2-7B-Chat2024.02 | 54.9 |