REBEL
Reported on 4 benchmarks across 2 tasks
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing3 results
- RE+ Macro F1 · uses extra data76.65
- RE+ Micro F1· uses extra data75.4best: 78.1 (ReLiK-Large)
- Relation F1· uses extra data41.8best: 47.1 (REBEL+pretraining)
Medical1 result
- Relation F1· uses extra data41.8best: 47.1 (REBEL+pretraining)