Question Answering on HotpotQA (EM)
45.67Exact MatchCoRect
Evaluation Results
| Method | Links | |
|---|---|---|
| CoRectModel=Qwen2.5-7b-instruct2026.02 | 45.67 | |
| AdaCADModel=Qwen2.5-7b-instruct2026.02 | 43.82 | |
| GreedyModel=Qwen2.5-7b-instruct2026.02 | 43.3 | |
| COIECDModel=Qwen2.5-7b-instruct2026.02 | 41.9 | |
| CoRectModel=LLaMA3-8b-instruct2026.02 | 41.15 | |
| AdaCADModel=LLaMA3-8b-instruct2026.02 | 40.43 | |
| CADModel=Qwen2.5-7b-instruct2026.02 | 40.31 | |
| GreedyModel=LLaMA3-8b-instruct2026.02 | 39.47 | |
| COIECDModel=LLaMA3-8b-instruct2026.02 | 37.1 | |
| CADModel=LLaMA3-8b-instruct2026.02 | 36.44 | |
| CoRectModel=Mistral-7b2026.02 | 36.06 | |
| AdaCADModel=Mistral-7b2026.02 | 34.69 | |
| GreedyModel=Mistral-7b2026.02 | 31.6 | |
| CoRectModel=LLaMA2-13b-chat2026.02 | 29.45 | |
| COIECDModel=Mistral-7b2026.02 | 29.23 | |
| CADModel=Mistral-7b2026.02 | 29.17 | |
| AdaCADModel=LLaMA2-13b-chat2026.02 | 29.13 | |
| CADModel=LLaMA2-13b-chat2026.02 | 23.53 | |
| GreedyModel=LLaMA2-13b-chat2026.02 | 21.27 | |
| COIECDModel=LLaMA2-13b-chat2026.02 | 20.83 |