Helpfulness Evaluation on SHP
89Helpfulness ScoreSelf-Examination
Evaluation Results
| Method | Links | |
|---|---|---|
| Self-ExaminationBase LLM=ChatGPT2025.08 | 89 | |
| Context FilteringBase LLM=ChatGPT2025.08 | 86 | |
| Context FilteringBase LLM=ChatGPT2025.08 | 82 | |
| ICDBase LLM=ChatGPT2025.08 | 81 | |
| Self-ReminderBase LLM=ChatGPT2025.08 | 80 | |
| No DefenseBase LLM=ChatGPT2025.08 | 76 | |
| Self-ExaminationBase LLM=ChatGPT2025.08 | 76 | |
| ICDBase LLM=ChatGPT2025.08 | 75 | |
| Self-ReminderBase LLM=ChatGPT2025.08 | 62 | |
| Context FilteringBase LLM=Llama22025.08 | 60 | |
| Context FilteringBase LLM=Llama22025.08 | 60 | |
| No DefenseBase LLM=Llama22025.08 | 57 | |
| No DefenseBase LLM=Llama22025.08 | 55 | |
| Self-ReminderBase LLM=Llama22025.08 | 54 | |
| Self-ReminderBase LLM=Llama22025.08 | 54 | |
| No DefenseBase LLM=ChatGPT2025.08 | 54 | |
| Context FilteringBase LLM=Vicuna2025.08 | 53 | |
| Safe DecodingBase LLM=Llama22025.08 | 50 | |
| Safe DecodingBase LLM=Llama22025.08 | 50 | |
| Context FilteringBase LLM=Vicuna2025.08 | 48 | |
| Self-ExaminationBase LLM=Vicuna2025.08 | 45 | |
| Safe DecodingBase LLM=Vicuna2025.08 | 45 | |
| Safe DecodingBase LLM=Vicuna2025.08 | 40 | |
| Self-ExaminationBase LLM=Vicuna2025.08 | 35 | |
| Intention AnalysisBase LLM=Vicuna2025.08 | 33 | |
| Intention AnalysisBase LLM=Vicuna2025.08 | 30 | |
| Self-ReminderBase LLM=Vicuna2025.08 | 29 | |
| No DefenseBase LLM=Vicuna2025.08 | 21 | |
| ICDBase LLM=Llama22025.08 | 21 | |
| ICDBase LLM=Llama22025.08 | 21 | |
| ICDBase LLM=Vicuna2025.08 | 20 | |
| Self-ReminderBase LLM=Vicuna2025.08 | 18 | |
| ICDBase LLM=Vicuna2025.08 | 18 | |
| No DefenseBase LLM=Vicuna2025.08 | 7 | |
| Self-ExaminationBase LLM=Llama22025.08 | 5 | |
| Self-ExaminationBase LLM=Llama22025.08 | 5 | |
| Intention AnalysisBase LLM=ChatGPT2025.08 | 4 | |
| Intention AnalysisBase LLM=ChatGPT2025.08 | 4 | |
| Intention AnalysisBase LLM=Llama22025.08 | 1 | |
| Intention AnalysisBase LLM=Llama22025.08 | 1 |