List your company
ResearchFormerly WizWand

Helpfulness Evaluation on SHP

89Helpfulness ScoreSelf-Examination
-2.5221.244568.76Aug 9, 2025
Updated 3mo ago

Evaluation results

MethodLinks
Self-ExaminationBase LLM=ChatGPT2025.0889
Context FilteringBase LLM=ChatGPT2025.0886
Context FilteringBase LLM=ChatGPT2025.0882
ICDBase LLM=ChatGPT2025.0881
Self-ReminderBase LLM=ChatGPT2025.0880
No DefenseBase LLM=ChatGPT2025.0876
Self-ExaminationBase LLM=ChatGPT2025.0876
ICDBase LLM=ChatGPT2025.0875
Self-ReminderBase LLM=ChatGPT2025.0862
Context FilteringBase LLM=Llama22025.0860
Context FilteringBase LLM=Llama22025.0860
No DefenseBase LLM=Llama22025.0857
No DefenseBase LLM=Llama22025.0855
Self-ReminderBase LLM=Llama22025.0854
Self-ReminderBase LLM=Llama22025.0854
No DefenseBase LLM=ChatGPT2025.0854
Context FilteringBase LLM=Vicuna2025.0853
Safe DecodingBase LLM=Llama22025.0850
Safe DecodingBase LLM=Llama22025.0850
Context FilteringBase LLM=Vicuna2025.0848
Self-ExaminationBase LLM=Vicuna2025.0845
Safe DecodingBase LLM=Vicuna2025.0845
Safe DecodingBase LLM=Vicuna2025.0840
Self-ExaminationBase LLM=Vicuna2025.0835
Intention AnalysisBase LLM=Vicuna2025.0833
Intention AnalysisBase LLM=Vicuna2025.0830
Self-ReminderBase LLM=Vicuna2025.0829
No DefenseBase LLM=Vicuna2025.0821
ICDBase LLM=Llama22025.0821
ICDBase LLM=Llama22025.0821
ICDBase LLM=Vicuna2025.0820
Self-ReminderBase LLM=Vicuna2025.0818
ICDBase LLM=Vicuna2025.0818
No DefenseBase LLM=Vicuna2025.087
Self-ExaminationBase LLM=Llama22025.085
Self-ExaminationBase LLM=Llama22025.085
Intention AnalysisBase LLM=ChatGPT2025.084
Intention AnalysisBase LLM=ChatGPT2025.084
Intention AnalysisBase LLM=Llama22025.081
Intention AnalysisBase LLM=Llama22025.081