List your company
ResearchFormerly WizWand

Hallucination Detection on SC-GPT4

76.4AUROCSELFCHECKGPT+f
49.56856.53463.570.466Jul 28, 2025
Updated 7mo ago

Evaluation results

MethodLinks
SELFCHECKGPT+fDetector=LLaMA 3.1, Future Context=true2025.0776.4
SELFCHECKGPTDetector=LLaMA 3.1, Future Context=false2025.0776
SC+fDetector=LLaMA 3.1, Future Context=true2025.0773.3
SELFCHECKGPT+fDetector=Gemma 3, Future Context=true2025.0772.5
SELFCHECKGPTDetector=Gemma 3, Future Context=false2025.0771.9
SELFCHECKGPT+fDetector=Qwen 2.5, Future Context=true2025.0770.3
DIRECT+fDetector=Qwen 2.5, Future Context=true2025.0769.1
DIRECT+fDetector=LLaMA 3.1, Future Context=true2025.0768
DIRECTDetector=Qwen 2.5, Future Context=false2025.0767.9
SELFCHECKGPTDetector=Qwen 2.5, Future Context=false2025.0767.8
SCDetector=LLaMA 3.1, Future Context=false2025.0765.8
SC+fDetector=Gemma 3, Future Context=true2025.0765.3
DIRECTDetector=LLaMA 3.1, Future Context=false2025.0763.8
SCDetector=Gemma 3, Future Context=false2025.0762.3
SC+fDetector=Qwen 2.5, Future Context=true2025.0760.5
DIRECT+fDetector=Gemma 3, Future Context=true2025.0758
DIRECTDetector=Gemma 3, Future Context=false2025.0753.4
SCDetector=Qwen 2.5, Future Context=false2025.0750.6