Question Answering with Abstention on SELFAWARE
91.4U-RefAbstain-R1
Evaluation Results
| Method | Links | |
|---|---|---|
| Abstain-R1Model=Abstain-R12026.04 | 91.4 | |
| Qwen2.5 3B InstructModel=Qwen2.5 3B Instruct2026.04 | 82.3 | |
| DeepSeek-V3Model=DeepSeek-V32026.04 | 72.1 | |
| Qwen2.5 7B InstructModel=Qwen2.5 7B Instruct2026.04 | 71.2 | |
| DeepSeek-R1Model=DeepSeek-R12026.04 | 63.8 | |
| Qwen2.5 32B InstructModel=Qwen2.5 32B Instruct2026.04 | 62.7 | |
| Llama3.1 8B InstructModel=Llama3.1 8B Instruct2026.04 | 49.8 |