Overrefusal Evaluation on JBench-B
92RRDb as Alpaca
Evaluation Results
| Method | Links | |
|---|---|---|
| Db as AlpacaSetting / Model=P-SFT, Llama22026.03 | 92 | |
| Db as AlpacaSetting / Model=RLVR, Llama3-U2026.03 | 67 | |
| BaselineSetting / Model=P-SFT, Llama22026.03 | 56 | |
| Db as Our DataSetting / Model=P-SFT, Llama22026.03 | 39 | |
| Db as Our DataSetting / Model=RLVR, Llama3-U2026.03 | 18 | |
| BaselineSetting / Model=RLVR, Llama3-U2026.03 | 10 |