Evidence-Based QA on GENSEARCH (test)
99.06Source QualityGPT-4
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GPT-4Evaluation Mode=Zero-shot2024.02 | 99.06 | 60.34 | |
| GPT-3.5Evaluation Mode=Zero-shot2024.02 | 96.23 | 54.68 | |
| Llama-2-13b-chatEvaluation Mode=Zero-shot2024.02 | 69.8 | 9.67 | |
| Zephyr-7b-βEvaluation Mode=Zero-shot2024.02 | 66.98 | 5.29 |