Machine Translation on FLORES-200 zho_Hant (devtest)
24Tie %GRPO
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| GRPOModel Scale=600M, Experiment=A, Sample Size=50 source sentences, Evaluation Protocol=Human preference (one-sided binomial test)2026.05 | 24 | 3.94 | 68 | — | 0.001 | |
| Baseline NLLB-200Model Scale=600M, Decoding=beam search, Fine-tuning=none, Sample Size=50 source sentences, Evaluation Protocol=Human preference (one-sided binomial test)2026.05 | 24 | — | — | 8 | 0.001 |