Question Answering on DROP history
68.52F1 ScoreToken-Guard
Evaluation Results
| Method | Links | |
|---|---|---|
| Token-Guard2026.01 | 68.52 | |
| Self-RAG2026.01 | 50.13 | |
| Self-Reflection2026.01 | 47.48 | |
| BaseModel2026.01 | 44.21 | |
| SELF-REFINE2026.01 | 42.64 |
| Method | Links | |
|---|---|---|
| Token-Guard2026.01 | 68.52 | |
| Self-RAG2026.01 | 50.13 | |
| Self-Reflection2026.01 | 47.48 | |
| BaseModel2026.01 | 44.21 | |
| SELF-REFINE2026.01 | 42.64 |