Age on Patchscopes few-shot 1.0 (test)
0.8965SRBALOR (S)
Evaluation Results
| Method | Links | |
|---|---|---|
| BALOR (S)Model=Llama3-8b, Evaluation Protocol=few-shot2026.01 | 0.8965 | |
| BALOR (S)Model=Qwen3-4b, Evaluation Protocol=few-shot2026.01 | 0.8658 | |
| BALOR (D)Model=Llama3-8b, Evaluation Protocol=few-shot2026.01 | 0.8448 | |
| BALOR (S)Model=Llama2-7b, Evaluation Protocol=few-shot2026.01 | 0.8048 | |
| BALOR (D)Model=Qwen3-4b, Evaluation Protocol=few-shot2026.01 | 0.7926 | |
| BALOR (D)Model=Llama2-7b, Evaluation Protocol=few-shot2026.01 | 0.7439 | |
| BALOR (S)Model=Llama3.2-1b, Evaluation Protocol=few-shot2026.01 | 0.6389 | |
| DBModel=Qwen3-4b, Evaluation Protocol=few-shot2026.01 | 0.6097 | |
| Fine-tuningModel=Llama2-7b, Evaluation Protocol=few-shot2026.01 | 0.5976 | |
| BALOR (D)Model=Llama3.2-1b, Evaluation Protocol=few-shot2026.01 | 0.5833 | |
| VanillaModel=Llama2-7b, Evaluation Protocol=few-shot2026.01 | 0.561 | |
| FairSteerModel=Llama3.2-1b, Evaluation Protocol=few-shot2026.01 | 0.5556 | |
| FairSteerModel=Llama2-7b, Evaluation Protocol=few-shot2026.01 | 0.5122 | |
| IEModel=Qwen3-4b, Evaluation Protocol=few-shot2026.01 | 0.5121 | |
| IEModel=Llama2-7b, Evaluation Protocol=few-shot2026.01 | 0.4878 | |
| FairSteerModel=Qwen3-4b, Evaluation Protocol=few-shot2026.01 | 0.4634 | |
| CBModel=Llama2-7b, Evaluation Protocol=few-shot2026.01 | 0.4268 | |
| Fine-tuningModel=Qwen3-4b, Evaluation Protocol=few-shot2026.01 | 0.4146 | |
| CBModel=Qwen3-4b, Evaluation Protocol=few-shot2026.01 | 0.4024 | |
| FairSteerModel=Llama3-8b, Evaluation Protocol=few-shot2026.01 | 0.3993 | |
| DBModel=Llama2-7b, Evaluation Protocol=few-shot2026.01 | 0.3902 | |
| VanillaModel=Qwen3-4b, Evaluation Protocol=few-shot2026.01 | 0.3902 | |
| DBModel=Llama3-8b, Evaluation Protocol=few-shot2026.01 | 0.3448 | |
| CBModel=Llama3-8b, Evaluation Protocol=few-shot2026.01 | 0.3103 | |
| IEModel=Llama3-8b, Evaluation Protocol=few-shot2026.01 | 0.2758 | |
| CBModel=Llama3.2-1b, Evaluation Protocol=few-shot2026.01 | 0.1944 | |
| VanillaModel=Llama3-8b, Evaluation Protocol=few-shot2026.01 | 0.1724 | |
| Fine-tuningModel=Llama3.2-1b, Evaluation Protocol=few-shot2026.01 | 0.1667 | |
| IEModel=Llama3.2-1b, Evaluation Protocol=few-shot2026.01 | 0.1389 | |
| Fine-tuningModel=Llama3-8b, Evaluation Protocol=few-shot2026.01 | 0.1034 | |
| DBModel=Llama3.2-1b, Evaluation Protocol=few-shot2026.01 | 0.0278 | |
| VanillaModel=Llama3.2-1b, Evaluation Protocol=few-shot2026.01 | 0 |