Refusal on Irrelevant Queries on DROP
92.03Refusal F1Doc2Atom
Evaluation Results
| Method | Links | |
|---|---|---|
| Doc2AtomBase Model=Gemma-2-2B-It2026.06 | 92.03 | |
| Doc2AtomBase Model=Qwen3-4B-Instruct2026.06 | 54.71 | |
| D2LckptBase Model=Qwen3-4B-Instruct2026.06 | 34.8 | |
| D2LrawBase Model=Qwen3-4B-Instruct2026.06 | 4.93 | |
| D2LrawBase Model=Gemma-2-2B-It2026.06 | 4.48 | |
| D2LatomBase Model=Gemma-2-2B-It2026.06 | 4.04 | |
| D2LckptBase Model=Gemma-2-2B-It2026.06 | 3.14 | |
| D2LatomBase Model=Qwen3-4B-Instruct2026.06 | 1.79 |