GROUP-ATT
Reported on 8 benchmarks across 4 tasks
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Knowledge Base4 results
- Accuracy (5-fold)66.9best: 94.3 (GPT-4 (Teaching-Inspired))
- Accuracy (training-test)69.5best: 87.1 (Multi-view* (ours))
- Accuracy (5-fold)66.9best: 94.3 (GPT-4 (Teaching-Inspired))
- Accuracy (training-test)69.5best: 87.1 (Multi-view* (ours))
Natural Language Processing2 results
- Accuracy (5-fold)66.9best: 94.3 (GPT-4 (Teaching-Inspired))
- Accuracy (training-test)69.5best: 87.1 (Multi-view* (ours))
Reasoning2 results
- Accuracy (5-fold)66.9best: 94.3 (GPT-4 (Teaching-Inspired))
- Accuracy (training-test)69.5best: 87.1 (Multi-view* (ours))