Multiple-choice tasks on TriviaQA
66.79AccuracyTruthX
Evaluation Results
| Method | Links | |
|---|---|---|
| TruthXBackbone=Llama-2-7B-Chat2024.02 | 66.79 | |
| Llama-2-7B-ChatBackbone=Llama-2-7B-Chat2024.02 | 66.75 | |
| ITIBackbone=Llama-2-7B-Chat2024.02 | 65.95 |
| Method | Links | |
|---|---|---|
| TruthXBackbone=Llama-2-7B-Chat2024.02 | 66.79 | |
| Llama-2-7B-ChatBackbone=Llama-2-7B-Chat2024.02 | 66.75 | |
| ITIBackbone=Llama-2-7B-Chat2024.02 | 65.95 |