Multilingual Question Answering on M3-Exam (test)
77.4Accuracy (All)EMCEE (Ours)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| EMCEE (Ours)Prompting Method=EMCEE (Ours), Backbone=GPT-4o-mini2025.03 | 77.4 | 83.3 | 71.5 | |
| EMCEE (ROUTE)Prompting Method=EMCEE (ROUTE), Backbone=GPT-4o-mini2025.03 | 76.2 | 83.1 | 69.2 | |
| ENG-COTPrompting Method=ENG-COT, Backbone=GPT-4o-mini2025.03 | 74.6 | 81.8 | 67.3 | |
| RAG (ENG)Prompting Method=RAG (ENG), Backbone=GPT-4o-mini2025.03 | 72.1 | 84 | 63.9 | |
| XLTPrompting Method=XLT, Backbone=GPT-4o-mini2025.03 | 70.4 | 76.9 | 63.8 | |
| NATIVE-COTPrompting Method=NATIVE-COT, Backbone=GPT-4o-mini2025.03 | 70.4 | 76.5 | 64.4 | |
| RAG (NATIVE)Prompting Method=RAG (NATIVE), Backbone=GPT-4o-mini2025.03 | 68.7 | 80.4 | 57 | |
| NATIVE-BASICPrompting Method=NATIVE-BASIC, Backbone=GPT-4o-mini2025.03 | 65.2 | 72.7 | 57.7 | |
| ENG-BASICPrompting Method=ENG-BASIC, Backbone=GPT-4o-mini2025.03 | 64.5 | 72.7 | 56.4 | |
| TRANS-GOOGLEPrompting Method=TRANS-GOOGLE, Backbone=GPT-4o-mini2025.03 | 59.9 | 70.1 | 49.8 |