Relevance Judgment Agreement on TREC-DL 2020 (test)
0.455Cohen's KappaRank1-7B
Evaluation Results
| Method | Links | |
|---|---|---|
| Rank1-7Badaptation=score thresholding, size=7B2026.01 | 0.455 | |
| UMBRELAadaptation=score thresholding2026.01 | 0.45 | |
| Rank1-14Badaptation=score thresholding, size=14B2026.01 | 0.438 | |
| Rank1-32Badaptation=score thresholding, size=32B2026.01 | 0.417 | |
| RankLLaMA-7Badaptation=score thresholding, size=7B2026.01 | 0.371 | |
| monoT5 3Badaptation=score thresholding, size=3B2026.01 | 0.364 | |
| RankLLaMA-13Badaptation=score thresholding, size=13B2026.01 | 0.34 | |
| monoT5 largeadaptation=score thresholding, size=large2026.01 | 0.311 | |
| monoT5 baseadaptation=score thresholding, size=base2026.01 | 0.307 |