Question Answering on 2Wiki (dev)
46.6Exact Match (EM)Thinker-Instruct
Evaluation Results
| Method | Links | |
|---|---|---|
| Thinker-InstructBase Model=Qwen2.5-3B, Number of Seeds=52026.05 | 46.6 | |
| SD-Search-BaseBase Model=Qwen2.5-3B, Number of Seeds=52026.05 | 42 | |
| AutoRefine-BaseBase Model=Qwen2.5-3B, Number of Seeds=52026.05 | 39 |