Question Answering on PubmedQA (F1)
43.21F1Self-RAG
Evaluation Results
| Method | Links | |
|---|---|---|
| Self-RAG2026.01 | 43.21 | |
| Token-Guard2026.01 | 29.67 | |
| SELF-REFINE2026.01 | 19.47 | |
| Self-Reflection2026.01 | 12.83 | |
| BaseModel2026.01 | 9.55 |
| Method | Links | |
|---|---|---|
| Self-RAG2026.01 | 43.21 | |
| Token-Guard2026.01 | 29.67 | |
| SELF-REFINE2026.01 | 19.47 | |
| Self-Reflection2026.01 | 12.83 | |
| BaseModel2026.01 | 9.55 |