QReCC
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Conversational Retrieval | QReCC (test) | Recall@1075.8 | 43 | |
| Conversational Query Retrieval | QReCC | R@1076.5 | 29 | |
| Conversational Search | QReCC (test) | MRR57.4 | 16 | |
| Answer Generation | QReCC | F1 Score31 | 16 | |
| Conversational response generation | QReCC | F1 Score31 | 15 | |
| Conversational Information Retrieval | QReCC (test) | R@1077.2 | 13 | |
| Conversational Question Answering | QReCC (test) | EM (%)120 | 12 | |
| Conversational Response Generation | QReCC (test) | F1 Score26.3 | 10 | |
| Question Rewriting | QRECC Mean/Overall 1.0 (test) | BLEU64.7 | 9 | |
| Question Rewriting | QRECC Easy 1.0 (test) | BLEU82.79 | 9 | |
| Question Rewriting | QRECC Medium subset 1.0 (test) | BLEU Score63.17 | 9 | |
| Question Rewriting | QRECC Hard subset 1.0 (test) | BLEU0.4948 | 9 | |
| Retrieval | QReCC | NDCG@339.6 | 8 | |
| Conversational Retrieval | QReCC | Top-1 Recall53.37 | 7 | |
| Knowledge-intensive dialog attribution | QReCC (dev) | Auto AIS (before)19.1 | 3 | |
| Conversational Search | QReCC large (test) | Recall@1063.7 | 2 |
Showing 16 of 16 rows