List your company

Generalization Performance Analysis on ID and OOD Evaluation Suite Combined

80.2Average AccuracyICR
49.31257.33165.3573.369Sep 26, 2025

Evaluation results

MethodLinks
ICRBackbone=Qwen2.5-7B2025.0980.20
Few-shot*Backbone=Qwen2.5-7B2025.0977.51
M²IVBackbone=Qwen2.5-7B2025.0976.23
LIVEBackbone=Qwen2.5-7B2025.0975.74
I2CLBackbone=Qwen2.5-7B2025.0975.63
Zero-shotBackbone=Qwen2.5-7B2025.0971.3—
Few-shot*Backbone=Llama2-7B2025.0966.81
ICRBackbone=Llama2-7B2025.0959.90
M²IVBackbone=Llama2-7B2025.0956.90
LIVEBackbone=Llama2-7B2025.0956.62
I2CLBackbone=Llama2-7B2025.09552
Zero-shotBackbone=Llama2-7B2025.0950.5—