Hallucination Detection on SelfCheckGPT (AUCPR)
43AUCPRSELFCHECKGPT
Evaluation Results
| Method | Links | |
|---|---|---|
| SELFCHECKGPTDetector=LLaMA 3.1, Future context=true2025.07 | 43 | |
| SELFCHECKGPTDetector=LLaMA 3.1, Future context=false2025.07 | 42.7 | |
| DIRECTDetector=LLaMA 3.1, Future context=true2025.07 | 36.4 | |
| DIRECTDetector=Qwen 2.5, Future context=true2025.07 | 34.6 | |
| DIRECTDetector=LLaMA 3.1, Future context=false2025.07 | 33.3 | |
| DIRECTDetector=Qwen 2.5, Future context=false2025.07 | 32.9 | |
| SELFCHECKGPTDetector=Gemma 3, Future context=true2025.07 | 32.5 | |
| SCDetector=LLaMA 3.1, Future context=true2025.07 | 31.9 | |
| DIRECTDetector=Gemma 3, Future context=true2025.07 | 30.1 | |
| SCDetector=Gemma 3, Future context=true2025.07 | 29.6 | |
| SELFCHECKGPTDetector=Qwen 2.5, Future context=false2025.07 | 29.6 | |
| SELFCHECKGPTDetector=Qwen 2.5, Future context=true2025.07 | 29.3 | |
| SCDetector=Qwen 2.5, Future context=true2025.07 | 28.9 | |
| SCDetector=LLaMA 3.1, Future context=false2025.07 | 28.6 | |
| DIRECTDetector=Gemma 3, Future context=false2025.07 | 28.6 | |
| SCDetector=Gemma 3, Future context=false2025.07 | 28.3 | |
| SELFCHECKGPTDetector=Gemma 3, Future context=false2025.07 | 27.4 | |
| SCDetector=Qwen 2.5, Future context=false2025.07 | 27.2 |