Value Alignment on Confucianism-4
3.842Conformity ScoreQ+IF
Evaluation Results
| Method | Links | |
|---|---|---|
| Q+IFTarget Model=Gemini-1.5-Flash, Judge=GPT-4o2025.07 | 3.842 | |
| PICACO2025.07 | 3.788 | |
| PICACOTarget Model=Gemini-1.5-Flash, Judge=GPT-4o2025.07 | 3.785 | |
| Q+IFTraining=SFT+2025.07 | 3.777 | |
| Q+IFModel=GPT-4o-mini2025.07 | 3.764 | |
| OPROTarget Model=Gemini-1.5-Flash, Judge=GPT-4o2025.07 | 3.764 | |
| MODULARTarget Model=Gemini-1.5-Flash, Judge=GPT-4o2025.07 | 3.751 | |
| Q+IF+COTTarget Model=Gemini-1.5-Flash, Judge=GPT-4o2025.07 | 3.749 | |
| URIALTarget Model=Gemini-1.5-Flash, Judge=GPT-4o2025.07 | 3.708 | |
| PICACOTarget Model=GPT-3.5-Turbo2025.07 | 3.598 | |
| URIAL+SUMTarget Model=Gemini-1.5-Flash, Judge=GPT-4o2025.07 | 3.597 | |
| OPROTarget Model=GPT-3.5-Turbo2025.07 | 3.53 | |
| Q+IFTarget Model=GPT-3.5-Turbo2025.07 | 3.522 | |
| QTarget Model=GPT-3.5-Turbo2025.07 | 3.491 | |
| MP+SYSTEM 1Target Model=Gemini-1.5-Flash, Judge=GPT-4o2025.07 | 3.46 | |
| QTarget Model=Gemini-1.5-Flash, Judge=GPT-4o2025.07 | 3.44 | |
| MP+SYSTEM 2Target Model=Gemini-1.5-Flash, Judge=GPT-4o2025.07 | 3.316 | |
| Q+IF2025.07 | 3.306 | |
| Q+IFTraining=SFT2025.07 | 3.258 | |
| CICLTarget Model=Gemini-1.5-Flash, Judge=GPT-4o2025.07 | 3.212 | |
| URIALTraining=SFT2025.07 | 2.805 | |
| URIALTarget Model=GPT-3.5-Turbo2025.07 | 2.648 |