Translation Error Detection on Salient Translation Error Detection (test)
60.8AccuracyAMPLIFY
Evaluation Results
| Method | Links | |
|---|---|---|
| AMPLIFYModel=GPT-3.5, Prompting Strategy=AMPLIFY2023.05 | 60.8 | |
| GPT-3.5Model=GPT-3.5, Prompting Strategy=CoT2023.05 | 54.7 | |
| AMPLIFYModel=GPT-3, Prompting Strategy=AMPLIFY2023.05 | 51.7 | |
| GPT-3Model=GPT-3, Prompting Strategy=CoT2023.05 | 50.2 | |
| GPT-3Model=GPT-3, Prompting Strategy=AO2023.05 | 48.2 | |
| GPT-3.5Model=GPT-3.5, Prompting Strategy=AO2023.05 | 43.2 | |
| Human-RaterModel=Human, Prompting Strategy=Average2023.05 | 36.7 | |
| SOTAModel=N/A, Prompting Strategy=N/A2023.05 | 31.9 | |
| RandomModel=N/A, Prompting Strategy=Random Choice2023.05 | 16.7 |