Hallucination Detection on SC-LLaMA (AUCPR)
93.4AUCPRSELFCHECKGPT
Evaluation Results
| Method | Links | |
|---|---|---|
| SELFCHECKGPTDetector=LLaMA 3.1, Future context=true2025.07 | 93.4 | |
| SELFCHECKGPTDetector=Gemma 3, Future context=true2025.07 | 93.2 | |
| SCDetector=LLaMA 3.1, Future context=true2025.07 | 92.5 | |
| SELFCHECKGPTDetector=LLaMA 3.1, Future context=false2025.07 | 92.2 | |
| SELFCHECKGPTDetector=Gemma 3, Future context=false2025.07 | 92 | |
| DIRECTDetector=LLaMA 3.1, Future context=true2025.07 | 91.5 | |
| DIRECTDetector=Qwen 2.5, Future context=true2025.07 | 91.4 | |
| SELFCHECKGPTDetector=Qwen 2.5, Future context=true2025.07 | 91.1 | |
| SCDetector=LLaMA 3.1, Future context=false2025.07 | 91 | |
| SCDetector=Gemma 3, Future context=true2025.07 | 90.8 | |
| DIRECTDetector=LLaMA 3.1, Future context=false2025.07 | 90.6 | |
| DIRECTDetector=Qwen 2.5, Future context=false2025.07 | 90.6 | |
| SELFCHECKGPTDetector=Qwen 2.5, Future context=false2025.07 | 90.5 | |
| SCDetector=Gemma 3, Future context=false2025.07 | 90.1 | |
| SCDetector=Qwen 2.5, Future context=true2025.07 | 89.4 | |
| DIRECTDetector=Gemma 3, Future context=true2025.07 | 88.3 | |
| DIRECTDetector=Gemma 3, Future context=false2025.07 | 88 | |
| SCDetector=Qwen 2.5, Future context=false2025.07 | 87.2 |