Question Answering on NQ (val) (F1)
62.1F1 ScoreM-ASK iterative search
Evaluation Results
| Method | Links | |
|---|---|---|
| M-ASK iterative searchModel Size=7B2026.05 | 62.1 | |
| QD-Retrieve-AnswerModel Size=14B2026.05 | 59.4 | |
| QD-Retrieve-Evidence-AnswerModel Size=14B2026.05 | 57.5 | |
| QD-Retrieve-AnswerModel Size=7B2026.05 | 53.6 | |
| QD-Retrieve-AnswerModel Size=3B2026.05 | 53.5 | |
| M-ASK iterative searchModel Size=1.5B2026.05 | 51.5 | |
| M-ASK iterative searchModel Size=3B2026.05 | 51.3 | |
| QD-Retrieve-Evidence-AnswerModel Size=7B2026.05 | 50.9 | |
| QD-Retrieve-AnswerModel Size=1.5B2026.05 | 50.8 | |
| QD-Retrieve-Evidence-AnswerModel Size=1.5B2026.05 | 48 | |
| QD-Retrieve-Evidence-AnswerModel Size=3B2026.05 | 47.3 | |
| QD-Retrieve-AnswerModel Size=0.5B2026.05 | 44.5 | |
| QD-Retrieve-Evidence-AnswerModel Size=0.5B2026.05 | 42.9 | |
| M-ASK iterative searchModel Size=0.5B2026.05 | 14.2 |