Safety and Utility Evaluation on Finance
0.004JSRMENTOR
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MENTORTarget Model=Qwen3-235B2025.11 | 0.004 | 4.918 | |
| DPP-MENTORTarget Model=GPT-4o2025.11 | 0.006 | 4.368 | |
| MENTORTarget Model=DeepSeek-R12025.11 | 0.006 | 4.856 | |
| MENTORTarget Model=Average2025.11 | 0.009 | 4.72 | |
| DPP-MENTORTarget Model=Qwen3-235B2025.11 | 0.01 | 4.908 | |
| DPP-MENTORTarget Model=Average2025.11 | 0.013 | 4.684 | |
| RePDTarget Model=Qwen3-235B2025.11 | 0.016 | 2.007 | |
| Self-ReminderTarget Model=Qwen3-235B2025.11 | 0.016 | 4.544 | |
| MENTORTarget Model=GPT-4o2025.11 | 0.016 | 4.386 | |
| DPP-MENTORTarget Model=DeepSeek-R12025.11 | 0.024 | 4.776 | |
| G4D-RuleTreeTarget Model=Qwen3-235B2025.11 | 0.028 | 4.516 | |
| G4DTarget Model=Qwen3-235B2025.11 | 0.03 | 4.642 | |
| G4D-RuleTreeTarget Model=Average2025.11 | 0.051 | 4.563 | |
| G4D-RuleTreeTarget Model=DeepSeek-R12025.11 | 0.058 | 4.7 | |
| G4D-RuleTreeTarget Model=GPT-4o2025.11 | 0.068 | 4.472 | |
| Self-ReminderTarget Model=Average2025.11 | 0.072 | 4.539 | |
| G4DTarget Model=Average2025.11 | 0.072 | 4.632 | |
| Self-ReminderTarget Model=GPT-4o2025.11 | 0.08 | 4.396 | |
| G4DTarget Model=GPT-4o2025.11 | 0.092 | 4.534 | |
| G4DTarget Model=DeepSeek-R12025.11 | 0.094 | 4.72 | |
| Self-ReminderTarget Model=DeepSeek-R12025.11 | 0.12 | 4.678 | |
| RePDTarget Model=DeepSeek-R12025.11 | 0.189 | 4.441 | |
| RePDTarget Model=Average2025.11 | 0.192 | 2.745 | |
| DPPTarget Model=Qwen3-235B2025.11 | 0.268 | 4.77 | |
| ProBTarget Model=Qwen3-235B2025.11 | 0.288 | 4.316 | |
| VanillaTarget Model=Qwen3-235B2025.11 | 0.3 | 4.854 | |
| RPO-MENTORTarget Model=Qwen3-235B2025.11 | 0.322 | 4.796 | |
| RePDTarget Model=GPT-4o2025.11 | 0.372 | 1.788 | |
| RPOTarget Model=Qwen3-235B2025.11 | 0.392 | 4.892 | |
| ProBTarget Model=Average2025.11 | 0.469 | 4.279 | |
| ProBTarget Model=DeepSeek-R12025.11 | 0.478 | 4.456 | |
| RPO-MENTORTarget Model=Average2025.11 | 0.479 | 4.581 | |
| RPO-MENTORTarget Model=DeepSeek-R12025.11 | 0.484 | 4.78 | |
| VanillaTarget Model=DeepSeek-R12025.11 | 0.522 | 4.924 | |
| DPPTarget Model=Average2025.11 | 0.535 | 4.752 | |
| VanillaTarget Model=Average2025.11 | 0.549 | 4.809 | |
| RPOTarget Model=Average2025.11 | 0.563 | 4.737 | |
| RPOTarget Model=DeepSeek-R12025.11 | 0.572 | 4.878 | |
| DPPTarget Model=DeepSeek-R12025.11 | 0.586 | 4.922 | |
| RPO-MENTORTarget Model=GPT-4o2025.11 | 0.632 | 4.166 | |
| ProBTarget Model=GPT-4o2025.11 | 0.642 | 4.066 | |
| RPOTarget Model=GPT-4o2025.11 | 0.726 | 4.442 | |
| DPPTarget Model=GPT-4o2025.11 | 0.75 | 4.564 | |
| VanillaTarget Model=GPT-4o2025.11 | 0.826 | 4.65 |