List your company

Hallucination Detection on SC-ChatGPT (AUCPR)

94.1AUCPRSELFCHECKGPT
85.57287.7869092.214Jul 28, 2025

Evaluation results

MethodLinks
SELFCHECKGPTDetector=LLaMA 3.1, Future context=true2025.0794.1
SELFCHECKGPTDetector=Gemma 3, Future context=true2025.0792.5
SELFCHECKGPTDetector=LLaMA 3.1, Future context=false2025.0792
SELFCHECKGPTDetector=Gemma 3, Future context=false2025.0791.7
DIRECTDetector=LLaMA 3.1, Future context=true2025.0791.5
SCDetector=LLaMA 3.1, Future context=true2025.0791.4
DIRECTDetector=Qwen 2.5, Future context=true2025.0790.8
SELFCHECKGPTDetector=Qwen 2.5, Future context=true2025.0790.6
SCDetector=Gemma 3, Future context=true2025.0790.1
SELFCHECKGPTDetector=Qwen 2.5, Future context=false2025.0790.1
DIRECTDetector=LLaMA 3.1, Future context=false2025.0790
DIRECTDetector=Qwen 2.5, Future context=false2025.0789.6
SCDetector=LLaMA 3.1, Future context=false2025.0789.1
SCDetector=Gemma 3, Future context=false2025.0788.6
SCDetector=Qwen 2.5, Future context=true2025.0788.4
DIRECTDetector=Gemma 3, Future context=true2025.0787.8
DIRECTDetector=Gemma 3, Future context=false2025.0786.3
SCDetector=Qwen 2.5, Future context=false2025.0785.9