LLM Robustness Evaluation on Handcrafted prompt
92BARRA-LLM
Evaluation results
| Method | Links | ||
|---|---|---|---|
| RA-LLMModel=Guanaco-7B-HF2023.09 | 92 | 9.3 | |
| Original LLMModel=Guanaco-7B-HF2023.09 | 95.3 | 94.7 | |
| Perplexity DefenseModel=Vicuna-7B-chat-HF2023.09 | 98 | 100 | |
| RA-LLMModel=Vicuna-7B-chat-HF2023.09 | 98.7 | 12 | |
| Original LLMModel=Vicuna-7B-chat-HF2023.09 | 99.3 | 98.7 | |
| Perplexity DefenseModel=Guanaco-7B-HF2023.09 | 100 | 100 |