Question Answering on TruthfulQA
Metric: BLEU (higher is better)
Metric: BLEU (higher is better)
| # | Model↕ | BLEU▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | UnifiedQA 3B | -0.16 | No | TruthfulQA: Measuring How Models Mimic Human Fal... | 2021-09-08 | Code |
| 2 | GPT-2 1.5B | -4.91 | No | TruthfulQA: Measuring How Models Mimic Human Fal... | 2021-09-08 | Code |
| 3 | GPT-J 6B | -7.58 | No | TruthfulQA: Measuring How Models Mimic Human Fal... | 2021-09-08 | Code |
| 4 | GPT-3 175B | -17.38 | No | TruthfulQA: Measuring How Models Mimic Human Fal... | 2021-09-08 | Code |