Relevance Judgment Agreement on TREC-DL 2022 (test)
0.43Cohen's KappaRank1-7B
Evaluation Results
| Method | Links | |
|---|---|---|
| Rank1-7Badaptation=score thresholding, size=7B2026.01 | 0.43 | |
| Rank1-32Badaptation=score thresholding, size=32B2026.01 | 0.426 | |
| Rank1-14Badaptation=score thresholding, size=14B2026.01 | 0.425 | |
| UMBRELAadaptation=score thresholding2026.01 | 0.421 | |
| monoT5 3Badaptation=score thresholding, size=3B2026.01 | 0.273 | |
| RankLLaMA-13Badaptation=score thresholding, size=13B2026.01 | 0.26 | |
| monoT5 largeadaptation=score thresholding, size=large2026.01 | 0.256 | |
| monoT5 baseadaptation=score thresholding, size=base2026.01 | 0.24 | |
| RankLLaMA-7Badaptation=score thresholding, size=7B2026.01 | 0.232 |