Machine Translation on En-Ru document-level
85.99d-COMETOurs
Evaluation results
| Method | Links | |
|---|---|---|
| OursBase Model=Mistral-Nemo-Instruct, Quality-aware fine-tuning=true2025.04 | 85.99 | |
| Doc2Doc (tuned)Base Model=Mistral-Nemo-Instruct2025.04 | 85.68 | |
| SentRefine (sent)Base Model=Mistral-Nemo-Instruct2025.04 | 85.63 | |
| Ours (-QA)Base Model=Mistral-Nemo-Instruct, Quality-aware fine-tuning=false2025.04 | 85.34 | |
| DocRefine (sent)Base Model=Mistral-Nemo-Instruct2025.04 | 84.67 | |
| Sent2Sent (tuned)Base Model=Mistral-Nemo-Instruct2025.04 | 84.58 | |
| CPLBase Model=Qwen3-8B, Input Type=Context-aware2026.03 | 84.36 | |
| CPLBase Model=Llama-3-8B-Instruct, Input Type=Context-aware2026.03 | 83.99 | |
| DocRefine (doc)Base Model=Mistral-Nemo-Instruct2025.04 | 83.9 | |
| OursBase Model=LLaMA-3-8B-Instruct, Quality-aware fine-tuning=true2025.04 | 83.85 | |
| Sent2SentBase Model=Mistral-Nemo-Instruct2025.04 | 83.78 | |
| SentRefine (sent)Base Model=LLaMA-3-8B-Instruct2025.04 | 83.74 | |
| Doc2DocBase Model=Mistral-Nemo-Instruct2025.04 | 83.66 | |
| Ours (-QA)Base Model=LLaMA-3-8B-Instruct, Quality-aware fine-tuning=false2025.04 | 83.17 | |
| DocRefine (doc)Base Model=LLaMA-3-8B-Instruct2025.04 | 83.16 | |
| CPLBase Model=Qwen3-4B, Input Type=Context-aware2026.03 | 83.09 | |
| Doc2Doc (tuned)Base Model=LLaMA-3-8B-Instruct2025.04 | 81.06 | |
| Sent2SentBase Model=LLaMA-3-8B-Instruct2025.04 | 80.97 | |
| Sent2Sent (tuned)Base Model=LLaMA-3-8B-Instruct2025.04 | 80.88 | |
| DocRefine (sent)Base Model=LLaMA-3-8B-Instruct2025.04 | 80.39 | |
| Doc2DocBase Model=LLaMA-3-8B-Instruct2025.04 | 80.18 |