List your company

Calibration on Bamboogle

0.113ECENAACL
0.097440.202470.30750.41253Jan 16, 2026

Evaluation results

MethodLinks
NAACLBackbone=Qwen2.5-7B-Instruct2026.010.11385.6
Noise-awareBackbone=Qwen2.5-7B-Instruct2026.010.19282.8
NAACLBackbone=Llama-3.1-8B-Instruct2026.010.19987.7
NAACLBackbone=DeepSeek-R1-Distill-Llama-8B2026.010.274.8
CoTBackbone=Qwen2.5-7B-Instruct2026.010.20879.8
EnsembleBackbone=Llama-3.1-8B-Instruct2026.010.21471.3
Label-only SFTBackbone=Qwen2.5-7B-Instruct2026.010.21682.1
Noise-awareBackbone=Llama-3.1-8B-Instruct2026.010.21779.3
VanillaBackbone=Qwen2.5-7B-Instruct2026.010.23680.9
EnsembleBackbone=Qwen2.5-7B-Instruct2026.010.2479.3
EnsembleBackbone=DeepSeek-R1-Distill-Llama-8B2026.010.2467.8
VanillaBackbone=DeepSeek-R1-Distill-Llama-8B2026.010.25169.3
NAACLBackbone=DeepSeek-R1-Distill-Qwen-7B2026.010.27179.3
Noise-awareBackbone=DeepSeek-R1-Distill-Llama-8B2026.010.28162.2
CoTBackbone=Llama-3.1-8B-Instruct2026.010.28855.2
CoTBackbone=DeepSeek-R1-Distill-Llama-8B2026.010.29468.7
Noise-awareBackbone=DeepSeek-R1-Distill-Qwen-7B2026.010.30469.7
Label-only SFTBackbone=Llama-3.1-8B-Instruct2026.010.30775.5
VanillaBackbone=DeepSeek-R1-Distill-Qwen-7B2026.010.31866.6
VanillaBackbone=Llama-3.1-8B-Instruct2026.010.32463.6
Label-only SFTBackbone=DeepSeek-R1-Distill-Llama-8B2026.010.34669.2
EnsembleBackbone=DeepSeek-R1-Distill-Qwen-7B2026.010.35660.1
CoTBackbone=DeepSeek-R1-Distill-Qwen-7B2026.010.38168.1
Label-only SFTBackbone=DeepSeek-R1-Distill-Qwen-7B2026.010.50257.4