List your company

Classification on Yahoo

3.53Expected Calibration Error (ECE)CaliDist_verbalized (As.)
2.311210.538118.76526.9919Jun 4, 2026

Evaluation results

MethodLinks
CaliDist_verbalized (As.)LLM=PHI-4-MINI 3.8B2026.063.5320.76
CaliDist (As.)LLM=Phi-4-mini (3.8B)2026.064.2519.69
CaliDist_verbalized (Pr.)LLM=PHI-4-MINI 3.8B2026.064.5820.85
CaliDist (Pr.)LLM=Phi-4-mini (3.8B)2026.065.5818.84
CaliDist_verbalized (Sa.)LLM=PHI-4-MINI 3.8B2026.065.6321.07
CaliDist (Sa.)LLM=Gemma-3 (4B)2026.065.7420.57
CaliDist (Pr.)LLM=Gemma-3 (4B)2026.065.8219.93
CaliDist (As.)LLM=Gemma-3 (4B)2026.066.821.11
CaliDist_verbalized (Sa.)LLM=GEMMA-3 4B2026.067.5620.53
CaliDist (Sa.)LLM=Phi-4-mini (3.8B)2026.067.7918.94
Temperature ScalingLLM=Phi-4-mini (3.8B)2026.068.8318.57
CaliDist_verbalized (As.)LLM=GEMMA-3 4B2026.068.8520.83
VerbalizedLLM=PHI-4-MINI 3.8B2026.0610.6421.95
CaliDist_verbalized (Pr.)LLM=GEMMA-3 4B2026.0613.4920.8
EntropyLLM=Phi-4-mini (3.8B)2026.0617.221.68
FSDLLM=Phi-4-mini (3.8B)2026.0618.4521.79
VanillaLLM=Phi-4-mini (3.8B)2026.0620.4322.72
VerbalizedLLM=GEMMA-3 4B2026.0623.1134.03
ConsistencyLLM=Phi-4-mini (3.8B)2026.0623.2124.08
Temperature ScalingLLM=Gemma-3 (4B)2026.0633.2733.01
ConsistencyLLM=Gemma-3 (4B)2026.0633.8334
FSDLLM=Gemma-3 (4B)2026.0633.9233.92
EntropyLLM=Gemma-3 (4B)2026.0633.9333.92
VanillaLLM=Gemma-3 (4B)2026.063434.03