Query Reformulation on 8,500 Body queries Reformulation V2
96.3Precision@1Gold (n=100)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Gold (n=100)Relevance Criteria=Loose Relevance2026.01 | 96.3 | 97.3 | 97.3 | |
| PRECISE-PPI (λ=0.95)Relevance Criteria=Loose Relevance2026.01 | 94 | 94.1 | 94.3 | |
| Sonnet-Unlb (binary)Relevance Criteria=Strict Relevance2026.01 | 85.5 | 84.8 | 84.3 | |
| Sonnet-Unlb (binary)Relevance Criteria=Loose Relevance2026.01 | 85.5 | 84.8 | 84.3 | |
| Sonnet-Unlb (prob)Relevance Criteria=Strict Relevance2026.01 | 77.6 | 77.6 | 77.6 | |
| Sonnet-Unlb (prob)Relevance Criteria=Loose Relevance2026.01 | 77.6 | 77.6 | 77.6 | |
| Gold (n=100)Relevance Criteria=Strict Relevance2026.01 | 62.6 | 62.6 | 63.6 | |
| PRECISE-PPI (λ=0.95)Relevance Criteria=Strict Relevance2026.01 | 59.7 | 59.2 | 59.4 |