List your company

Text Classification on Yahoo! Answers (ECE, BS)

3.04ECECaliDist_verbalized (As.)
1.96729.208616.4523.6914Jun 4, 2026

Evaluation results

MethodLinks
CaliDist_verbalized (As.)LLM=QWEN-2 7B2026.063.0419.82
CaliDist_verbalized (Pr.)LLM=QWEN-2 7B2026.063.2919.71
CaliDist_verbalized (Pr.)LLM=LLAMA-3.1 8B2026.063.5118.47
CaliDist (As.)LLM=QWEN-3 8B2026.063.7318.47
CaliDist_verbalized (Sa.)LLM=QWEN-2 7B2026.063.8519.97
CaliDist (As.)LLM=LLAMA-3.1 8B2026.064.1116.88
CaliDist (Pr.)LLM=LLAMA-3.1 8B2026.064.5616.89
CaliDist_verbalized (As.)LLM=LLAMA-3.1 8B2026.064.9618.65
CaliDist_verbalized (Sa.)LLM=LLAMA-3.1 8B2026.065.0718.75
CaliDist (Pr.)LLM=QWEN-3 8B2026.065.1118.49
CaliDist (Sa.)LLM=LLAMA-3.1 8B2026.065.8517.2
CaliDist (Sa.)LLM=QWEN-3 8B2026.066.5319.62
Temperature ScalingLLM=LLAMA-3.1 8B2026.0612.6417.72
VerbalizedLLM=QWEN-2 7B2026.0613.121.33
VerbalizedLLM=LLAMA-3.1 8B2026.0616.8221.1
VanillaLLM=LLAMA-3.1 8B2026.0619.7421.18
EntropyLLM=LLAMA-3.1 8B2026.0619.8921.25
FSDLLM=LLAMA-3.1 8B2026.0621.0422.65
ConsistencyLLM=LLAMA-3.1 8B2026.0625.0124.82
Temperature ScalingLLM=QWEN-3 8B2026.0628.4528.36
EntropyLLM=QWEN-3 8B2026.0629.0529.21
VanillaLLM=QWEN-3 8B2026.0629.4229.38
FSDLLM=QWEN-3 8B2026.0629.5229.57
ConsistencyLLM=QWEN-3 8B2026.0629.8629.89