Evidence-Based QA on SYNSCIQA (test)
62.71Source QualityGPT-4
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GPT-4Evaluation Mode=Zero-shot2024.02 | 62.71 | 86.28 | |
| GPT-3.5Evaluation Mode=Zero-shot2024.02 | 53.25 | 64.93 | |
| Llama-2-13b-chatEvaluation Mode=Zero-shot2024.02 | 49.91 | 25.01 | |
| Zephyr-7b-βEvaluation Mode=Zero-shot2024.02 | 36.92 | 13.01 |