List your company

Annotator Simulation on VariErr

63.8Label AccuracySFT
30.20838.92947.6556.371May 27, 2026

Evaluation results

MethodLinks
SFTBackbone=Qwen32026.0563.828.30.08484.50.85930
CAPOBackbone=Qwen32026.0562.728.10.08186.70.88832.8
VP-ICLBackbone=Qwen32026.0554.520.10.47649.40.52828.2
ICLBackbone=Qwen32026.0553.518.60.69234.40.17926.5
SFTBackbone=Llama3.22026.0551.227.10.11390.90.94628.2
CAPOBackbone=Llama3.22026.0551.226.20.12192.40.96429.7
VPBackbone=Qwen32026.0549.213.14.39123.4-0.34824
BaseBackbone=Qwen32026.0547.215.92.39423.9-0.03423.7
VP-ICLBackbone=Llama3.22026.0541.2210.539260.43227.5
ICLBackbone=Llama3.22026.053821.40.47629.50.37526
VPBackbone=Llama3.22026.0533.814.81.90735.80.32525.3
BaseBackbone=Llama3.22026.0531.515.32.03625.80.02326.5