Targeted Poisoning on TruthfulQA Two options
66.24Benign F1 ScoreAAP
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| AAPModel=Qwen2.5-7B2025.05 | 66.24 | 66.24 | 36.34 | 35.82 | 51.29 | 51.03 | |
| PARASITEModel=Qwen2.5-7B2025.05 | 62.76 | 61.75 | 73.03 | 72.07 | 67.89 | 66.91 | |
| ManualModel=Qwen2.5-7B2025.05 | 58.39 | 52.67 | 41.52 | 40.36 | 49.95 | 46.52 | |
| PARASITEModel=Deepseek-7B2025.05 | 55.29 | 46.47 | 58.92 | 54 | 57.11 | 50.23 | |
| NSPModel=Deepseek-7B2025.05 | 53.12 | 51.67 | 39.38 | 37.82 | 46.25 | 44.75 | |
| AAPModel=Deepseek-7B2025.05 | 52.75 | 45.32 | 49.66 | 44.36 | 51.2 | 44.84 | |
| NSPModel=Qwen2.5-7B2025.05 | 52.33 | 52.33 | 51.33 | 51.09 | 51.83 | 51.71 | |
| ManualModel=Deepseek-7B2025.05 | 26.67 | 26.67 | 34.67 | 34.55 | 30.67 | 30.61 | |
| ECLIPSEModel=Qwen2.5-7B2025.05 | 16.19 | 3.95 | 15.17 | 1.82 | 15.68 | 2.89 | |
| ECLIPSEModel=Deepseek-7B2025.05 | 11.86 | 3.29 | 9.68 | 2.96 | 10.77 | 3.13 |