List your company
ResearchFormerly WizWand

Hallucination Detection on SC-Vicuna

71.4AUROCSC+f
55.38459.54263.767.858Jul 28, 2025
Updated 7mo ago

Evaluation results

MethodLinks
SC+fDetector=LLaMA 3.1, Future Context=true2025.0771.4
SELFCHECKGPT+fDetector=LLaMA 3.1, Future Context=true2025.0770.2
SELFCHECKGPT+fDetector=Gemma 3, Future Context=true2025.0770.1
SELFCHECKGPTDetector=LLaMA 3.1, Future Context=false2025.0769.6
DIRECT+fDetector=LLaMA 3.1, Future Context=true2025.0768.4
DIRECTDetector=LLaMA 3.1, Future Context=false2025.0768
SELFCHECKGPTDetector=Gemma 3, Future Context=false2025.0767.7
SC+fDetector=Gemma 3, Future Context=true2025.0767.7
SCDetector=LLaMA 3.1, Future Context=false2025.0767.3
SCDetector=Gemma 3, Future Context=false2025.0765.7
SELFCHECKGPTDetector=Qwen 2.5, Future Context=false2025.0765.7
DIRECT+fDetector=Qwen 2.5, Future Context=true2025.0765.6
DIRECTDetector=Qwen 2.5, Future Context=false2025.0765.5
SELFCHECKGPT+fDetector=Qwen 2.5, Future Context=true2025.0765.1
SC+fDetector=Qwen 2.5, Future Context=true2025.0760.2
DIRECT+fDetector=Gemma 3, Future Context=true2025.0757.5
DIRECTDetector=Gemma 3, Future Context=false2025.0756.6
SCDetector=Qwen 2.5, Future Context=false2025.0756