Hallucination Detection (AUCPR) on SC-GPT4
95.3AUCPRSELFCHECKGPT
Evaluation Results
| Method | Links | |
|---|---|---|
| SELFCHECKGPTDetector=LLaMA 3.1, Future context=true2025.07 | 95.3 | |
| SELFCHECKGPTDetector=LLaMA 3.1, Future context=false2025.07 | 94.7 | |
| SELFCHECKGPTDetector=Gemma 3, Future context=true2025.07 | 94.4 | |
| SCDetector=LLaMA 3.1, Future context=true2025.07 | 94.2 | |
| SELFCHECKGPTDetector=Gemma 3, Future context=false2025.07 | 93.8 | |
| SELFCHECKGPTDetector=Qwen 2.5, Future context=true2025.07 | 93.3 | |
| DIRECTDetector=Qwen 2.5, Future context=true2025.07 | 93 | |
| SELFCHECKGPTDetector=Qwen 2.5, Future context=false2025.07 | 92.6 | |
| DIRECTDetector=LLaMA 3.1, Future context=true2025.07 | 92.4 | |
| DIRECTDetector=Qwen 2.5, Future context=false2025.07 | 92.4 | |
| SCDetector=LLaMA 3.1, Future context=false2025.07 | 91.7 | |
| SCDetector=Gemma 3, Future context=true2025.07 | 91.7 | |
| DIRECTDetector=LLaMA 3.1, Future context=false2025.07 | 91.1 | |
| SCDetector=Gemma 3, Future context=false2025.07 | 90.8 | |
| SCDetector=Qwen 2.5, Future context=true2025.07 | 90.6 | |
| DIRECTDetector=Gemma 3, Future context=true2025.07 | 89.5 | |
| DIRECTDetector=Gemma 3, Future context=false2025.07 | 88.8 | |
| SCDetector=Qwen 2.5, Future context=false2025.07 | 88.2 |