Multilingual Knowledge Question Answering on MKQA (test)
52.3F1-score (All)EMCEE (Ours)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| EMCEE (Ours)Prompting Method=EMCEE (Ours), Backbone=GPT-4o-mini2025.03 | 52.3 | 52.2 | 52.4 | |
| XLTPrompting Method=XLT, Backbone=GPT-4o-mini2025.03 | 51.1 | 50.9 | 51.5 | |
| EMCEE (ROUTE)Prompting Method=EMCEE (ROUTE), Backbone=GPT-4o-mini2025.03 | 50.8 | 51.6 | 49.8 | |
| TRANS-GOOGLEPrompting Method=TRANS-GOOGLE, Backbone=GPT-4o-mini2025.03 | 50.3 | 50.4 | 50.2 | |
| ENG-COTPrompting Method=ENG-COT, Backbone=GPT-4o-mini2025.03 | 49.4 | 49.5 | 49.3 | |
| ENG-BASICPrompting Method=ENG-BASIC, Backbone=GPT-4o-mini2025.03 | 48.1 | 49.8 | 46 | |
| NATIVE-COTPrompting Method=NATIVE-COT, Backbone=GPT-4o-mini2025.03 | 45.5 | 49.2 | 40.9 | |
| RAG (ENG)Prompting Method=RAG (ENG), Backbone=GPT-4o-mini2025.03 | 44.7 | 44.9 | 44.5 | |
| NATIVE-BASICPrompting Method=NATIVE-BASIC, Backbone=GPT-4o-mini2025.03 | 44.1 | 48.6 | 38.5 | |
| RAG (NATIVE)Prompting Method=RAG (NATIVE), Backbone=GPT-4o-mini2025.03 | 42.5 | 45.3 | 39 |