Evidence-Based QA on CLIMATEQA (test)
28.01AttributabilityGPT-4
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4Evaluation Mode=Zero-shot2024.02 | 28.01 | |
| GPT-3.5Evaluation Mode=Zero-shot2024.02 | 18.93 | |
| Zephyr-7b-βEvaluation Mode=Zero-shot2024.02 | 2.3 | |
| Llama-2-13b-chatEvaluation Mode=Zero-shot2024.02 | 2.13 |