Machine Translation on WMT22 En-Hr (news)
87.8COMETIBUT
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| IBUTMode=Iterative Bilingual Understanding (IBUT)2024.10 | 87.8 | 77.1 | 28.5 | |
| ChatGPTMode=Translation Error Analysis and Reduction (TEaR)2024.10 | 87.2 | 76.2 | 27.5 | |
| ChatGPTMode=Multi-Agent Discussion (MAD)2024.10 | 87 | 76.9 | 26.5 | |
| ChatGPTMode=Iterative Refinement2024.10 | 87 | 76.9 | 27.5 | |
| ChatGPTMode=Zero-shot2024.10 | 86.6 | 76.8 | 26.9 | |
| ChatGPTMode=Multi-Agent Prompt Selection (MAPS)2024.10 | 86.5 | 76 | 27 | |
| ChatGPTMode=5-shot prompting2024.10 | 86.4 | 75.6 | 25.8 | |
| ChatGPTMode=Reranking2024.10 | 86.3 | 75.4 | 26.9 | |
| ChatGPTMode=Dual-Reflection2024.10 | 58.2 | 76.9 | 26.4 |