Question Answering on Translated TruthfulQA (test)
81.4Accuracy - EnglishGPT-4o
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| GPT-4oshot=0-shot2024.10 | 81.4 | 55.4 | 59.2 | 59.1 | 64.4 | 51.1 | |
| GPT-4shot=0-shot2024.10 | 81.3 | 42.6 | 37.6 | 42.9 | 62 | 41.3 | |
| GPT-4o minishot=0-shot2024.10 | 66.5 | 33.9 | 42.1 | 36.1 | 48.4 | 35.8 | |
| GPT 3.5 Turboshot=0-shot2024.10 | 53.6 | 26.1 | 29.1 | 29.3 | 40 | 28.3 |