Sports Understanding on FLORES-200 (10 Low-Resourced Languages Subset)
58.8Kazakh (Cyrl) ScoreDIP
Evaluation results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DIPModel=GPT-4o, English Pivoting=true, Chain-of-thought=true2024.11 | 58.8 | 64.4 | 67.2 | 60.8 | 62.4 | 59.6 | 58.8 | 64 | 63.2 | 59.2 | 61.84 | |
| DIP w/ EP w/o CTModel=GPT-4o, English Pivoting=true, Chain-of-thought=false2024.11 | 56.4 | 54.8 | 64 | 60.4 | 60.4 | 60.4 | 56.4 | 54.8 | 58.8 | 54.4 | 58.08 | |
| Standard PromptingModel=GPT-4o2024.11 | 49.6 | 56 | 42.8 | 56.8 | 55.6 | 53.2 | 43.6 | 54 | 27.2 | 45.2 | 48.4 | |
| Non-insertion PromptingModel=GPT-4o2024.11 | 48.4 | 47.6 | 46 | 51.6 | 50 | 52.4 | 41.6 | 48.8 | 52.8 | 54.4 | 49.36 | |
| English PivotingModel=GPT-4o2024.11 | 48.4 | 48.8 | 50.8 | 48 | 42.8 | 47.6 | 52.4 | 47.6 | 51.6 | 45.6 | 48.36 | |
| English Pivot ThoughtModel=GPT-4o2024.11 | 47.2 | 50.4 | 46.8 | 46.8 | 46 | 47.2 | 47.6 | 46.8 | 46.8 | 46 | 47.16 | |
| DIP w/o EP w/o CTModel=GPT-4o, English Pivoting=false, Chain-of-thought=false2024.11 | 46.8 | 50 | 46.8 | 55.2 | 56.8 | 56 | 42.8 | 56.8 | 22 | 52.4 | 48.56 |