Document-level Relation Extraction on Re-DocRED Full Dataset 1.0 (test)
79.39PrecisionDREEAM-DOREMI
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DREEAM-DOREMICategory=RoBERTa, Backbone=RoBERTa, Training Strategy=DOREMI iterative training2026.01 | 79.39 | 68.94 | 72.67 | 75.88 | 70.75 | |
| DREEAM-DOREMICategory=BERT, Backbone=BERT, Training Strategy=DOREMI iterative training2026.01 | 77.01 | 65.76 | 70.37 | 73.54 | 67.99 | |
| ATLOP-DOREMICategory=RoBERTa, Backbone=RoBERTa, Training Strategy=DOREMI iterative training2026.01 | 74.86 | 63.11 | 70.23 | 72.47 | 66.48 | |
| ATLOP-DOREMICategory=BERT, Backbone=BERT, Training Strategy=DOREMI iterative training2026.01 | 74.8 | 62.97 | 69.14 | 71.86 | 65.91 | |
| GPT-4.1Category=LLMs, Zero-shot=true, Temperature=0.752026.01 | 16.12 | — | 3.01 | 5.79 | — | |
| Llama-3.3-70BCategory=LLMs, Zero-shot=true, Temperature=0.72026.01 | 1.98 | — | 0.15 | 0.28 | — |