Machine Translation on WMT Cs-Uk 22
90.2COMET ScoreDUAL-REFLECT
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DUAL-REFLECTbackbone=ChatGPT, prompting=zero-shot2024.06 | 90.2 | 77.3 | |
| ChatGPT + Refine_cosprompting=zero-shot2024.06 | 89.5 | 75 | |
| ChatGPT + Refineprompting=zero-shot2024.06 | 89 | 74.5 | |
| ChatGPT + MAPSprompting=zero-shot2024.06 | 88.8 | 76.1 | |
| ChatGPT + Self-Reflectprompting=zero-shot2024.06 | 88.4 | 76 | |
| ChatGPTprompting=5-shot2024.06 | 88.3 | — | |
| ChatGPT + Rerankprompting=zero-shot2024.06 | 88.3 | 75.3 | |
| ChatGPTprompting=zero-shot2024.06 | 88 | 75 | |
| DUAL-REFLECTbackbone=Vicuna-7B, prompting=zero-shot2024.06 | 78.3 | 60.7 | |
| DUAL-REFLECTbackbone=Alpaca-7B, prompting=zero-shot2024.06 | 77.5 | 54.3 | |
| Vicuna-7B + MAPSprompting=zero-shot2024.06 | 77.2 | 59.6 | |
| Alpaca-7B + MAPSprompting=zero-shot2024.06 | 76.3 | 53.7 | |
| Vicuna-7Bprompting=5-shot2024.06 | 76.3 | 58.3 | |
| Alpaca-7Bprompting=5-shot2024.06 | 75.9 | 53.1 | |
| Vicuna-7Bprompting=zero-shot2024.06 | 74.9 | 57.8 | |
| Alpaca-7Bprompting=zero-shot2024.06 | 74.1 | 52.4 |