List your company

Uncertainty Estimation on MoreHopQA Camel

65.29AUROCMATU
50.251654.155858.0661.9642Apr 9, 2026

Evaluation results

MethodLinks
MATUBase LLM=Qwen2.5-7B2026.0465.2972.26
MATUBase LLM=Llama3.1-8B2026.0463.265.61
P(true)Base LLM=Qwen2.5-7B2026.0457.6665.12
SAUP-MultipleBase LLM=Llama3.1-8B2026.0456.6857.98
Eigv(Agre)-finalBase LLM=Qwen2.5-7B2026.0456.3165.29
Eigv(Agre)-finalBase LLM=Llama3.1-8B2026.0455.7256.44
MATUBase LLM=GPT-4o2026.0455.5534.74
P(true)Base LLM=GPT-4o2026.0454.834.05
Eigv(Agre)-WholeBase LLM=Qwen2.5-7B2026.0454.263.42
Eigv(Agre)-WholeBase LLM=Llama3.1-8B2026.0453.9855.85
SAUP-MultipleBase LLM=Qwen2.5-7B2026.0453.8663.45
P(true)Base LLM=Llama3.1-8B2026.0453.1354.6
Eigv(Agre)-finalBase LLM=GPT-4o2026.0453.0733.74
Eigv(Agre)-WholeBase LLM=GPT-4o2026.0452.5933.19
SAUP-SingleBase LLM=Qwen2.5-7B2026.0451.0362.11
SAUP-SingleBase LLM=Llama3.1-8B2026.0450.8355.76