Multitask Language Understanding on MMMLU (target)
55.14AccuracyBaseline
Evaluation results
| Method | Links | |
|---|---|---|
| BaselineN=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 55.14 | |
| TLPON=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 53.83 | |
| ORPON=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 50.18 | |
| DPON=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 48.37 | |
| SFTN=16, setting=English occurrence as language confusion, aggregation=Averaged across four models and four target languages2026.04 | 46.54 |