Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Coreference Resolution on GENIA coreference
Loading...
91.6
Macro F1
Fine-tuned Constrained Macaw-3B
71.32
76.585
81.85
87.115
Aug 20, 2025
Macro F1
Updated 22d ago
Evaluation Results
Method
Method
Links
Macro F1
Fine-tuned Constrained Macaw-3B
Backbone=Macaw-3B, Eva...
2025.08
91.6
Local Fine-tuned + Local Calibration (+ constr)
Evaluation Protocol=Lo...
2025.08
89.1
Global Fine Tuning
Evaluation Protocol=Gl...
2025.08
89
Local Fine-tuned baseline (+ constr)
Evaluation Protocol=Lo...
2025.08
88.7
Local Fine-tuned baseline
Evaluation Protocol=Lo...
2025.08
88.3
Local Fine-tuned + Local Calibration
Evaluation Protocol=Lo...
2025.08
88.2
Local Fine-tuned + Global Calibration
Evaluation Protocol=Lo...
2025.08
88.1
Pre-trained Global Calibration
Evaluation Protocol=Pr...
2025.08
80.5
Pre-trained Local Calibration (+ constr)
Evaluation Protocol=Pr...
2025.08
80
Pre-trained Local Calibration
Evaluation Protocol=Pr...
2025.08
77.1
Pre-trained few-shot baseline (+ constr)
Evaluation Protocol=Pr...
2025.08
75.9
Pre-trained few-shot baseline
Evaluation Protocol=Pr...
2025.08
72.1
Feedback
Search any
task
Search any
task