| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Relevance | ALCE | Kendall's Tau0.61 | 15 | |
| Citation-aware Question Answering | ALCE ASQA | EM Recall43.1 | 13 | |
| Citation-aware Question Answering | ALCE ELI5 | EM Recall21.4 | 12 | |
| Completeness | ALCE | Kendall's Tau0.47 | 11 | |
| Long-form Question Answering | ALCE LFQA | ROUGE-L38.6 | 7 | |
| RAG-Completeness | ALCE (test) | Mean Kendall's Tau0.47 | 6 |