IPI Sanitization on Jfleg RTE (unseen)
0ASRRENNERVATE
Evaluation Results
| Method | Links | |
|---|---|---|
| RENNERVATETarget LLM=Falcon2025.12 | 0 | |
| RENNERVATETarget LLM=LLaMA22025.12 | 0 | |
| RENNERVATETarget LLM=LLaMA32025.12 | 0 | |
| RENNERVATETarget LLM=ChatGLM2025.12 | 0.5 | |
| RENNERVATETarget LLM=LLaMA22025.12 | 0.7 | |
| RENNERVATETarget LLM=ChatGLM2025.12 | 2.1 | |
| RENNERVATETarget LLM=Dolly2025.12 | 4.7 | |
| RENNERVATETarget LLM=LLaMA32025.12 | 5.2 | |
| NoneTarget LLM=Falcon2025.12 | 9.8 | |
| RENNERVATETarget LLM=Dolly2025.12 | 10.9 | |
| RENNERVATETarget LLM=Falcon2025.12 | 14.5 | |
| NoneTarget LLM=Dolly2025.12 | 23 | |
| NoneTarget LLM=ChatGLM2025.12 | 34 | |
| NoneTarget LLM=LLaMA22025.12 | 57.5 | |
| NoneTarget LLM=Dolly2025.12 | 58.5 | |
| NoneTarget LLM=LLaMA22025.12 | 59 | |
| NoneTarget LLM=LLaMA32025.12 | 84.9 | |
| NoneTarget LLM=Falcon2025.12 | 94.4 | |
| NoneTarget LLM=LLaMA32025.12 | 97.1 | |
| NoneTarget LLM=ChatGLM2025.12 | 98.2 |