Open-domain Question Answering on Bamboogle Search-o1 framework (test)
34.9AccuracyPROBE&PREFILL
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| PROBE&PREFILLN=632026.05 | 34.9 | 87 | -54 | |
| Best BaselineN=632026.05 | 33.3 | 145 | -23 | |
| DefaultN=632026.05 | 25.4 | 188 | — |
| Method | Links | |||
|---|---|---|---|---|
| PROBE&PREFILLN=632026.05 | 34.9 | 87 | -54 | |
| Best BaselineN=632026.05 | 33.3 | 145 | -23 | |
| DefaultN=632026.05 | 25.4 | 188 | — |