Factual Reasoning on SampleQA (Accuracy)
3.21AccuracyVRPO
Evaluation Results
| Method | Links | |
|---|---|---|
| VRPOBase Model=Qwen3-8B2025.08 | 3.21 | |
| KTAEBase Model=Qwen3-8B2025.08 | 3.17 | |
| λ-GRPOBase Model=Qwen2.5-7B-Cold Start2025.08 | 2.94 | |
| BaseBase Model=Qwen3-8B2025.08 | 2.89 | |
| VRPOBase Model=Qwen2.5-7B-Cold Start2025.08 | 2.82 | |
| λ-GRPOBase Model=Qwen3-8B2025.08 | 2.77 | |
| BaseBase Model=Qwen2.5-7B-Cold Start2025.08 | 2.36 | |
| KTAEBase Model=Qwen2.5-7B-Cold Start2025.08 | 1.73 |