List your company

Uncertainty Estimation on SVAMP

68.8ROC-AUC (128)DiSE
55.69659.09862.565.902Mar 3, 2026

Evaluation results

MethodLinks
DiSEBackbone=LLaDA-Instruct-8B2026.0368.8—69.275.5
LLaMA perplexityBackbone=LLaDA-Instruct-8B, Evaluation Model=LLaMA3-Instruct-8B2026.0368.6—6559
LLaMA perplexityBackbone=LLaDA-1.5-8B, Evaluation Model=LLaMA3-Instruct-8B2026.0363.9—58.762
MCBackbone=LLaDA-Instruct-8B, Nmc=322026.0361.6—55.164.7
DiSEBackbone=LLaDA-1.5-8B2026.0359.9—62.967.7
MCBackbone=LLaDA-1.5-8B, Nmc=322026.0358.5—51.359.7
MCBackbone=LLaDA-Instruct-8B, Nmc=12026.0356.3—57.550.9
MCBackbone=LLaDA-1.5-8B, Nmc=12026.0356.2—46.655.4
BSDETECTORLLM=Text-Davinci-0032023.08—93.6——
BSDETECTORLLM=GPT-3.5 Turbo2023.08—92.7——
Likelihood Based UncertaintyLLM=Text-Davinci-0032023.08—66.8——
Self-reflection CertaintyLLM=Text-Davinci-0032023.08—61.9——
Self-reflection CertaintyLLM=GPT-3.5 Turbo2023.08—83.9——
Temperature SamplingLLM=Text-Davinci-0032023.08—65.3——
Temperature SamplingLLM=GPT-3.5 Turbo2023.08—67.1——