Hallucination Detection on SC-ChatGPT
74.9AUROCSELFCHECKGPT+f
Evaluation Results
| Method | Links | |
|---|---|---|
| SELFCHECKGPT+fDetector=LLaMA 3.1, Future Context=true2025.07 | 74.9 | |
| SELFCHECKGPTDetector=LLaMA 3.1, Future Context=false2025.07 | 71.2 | |
| SELFCHECKGPT+fDetector=Gemma 3, Future Context=true2025.07 | 71 | |
| SC+fDetector=LLaMA 3.1, Future Context=true2025.07 | 69.2 | |
| DIRECT+fDetector=LLaMA 3.1, Future Context=true2025.07 | 69 | |
| SELFCHECKGPTDetector=Gemma 3, Future Context=false2025.07 | 68.8 | |
| DIRECTDetector=LLaMA 3.1, Future Context=false2025.07 | 66.4 | |
| DIRECT+fDetector=Qwen 2.5, Future Context=true2025.07 | 65.8 | |
| SC+fDetector=Gemma 3, Future Context=true2025.07 | 65.6 | |
| SELFCHECKGPT+fDetector=Qwen 2.5, Future Context=true2025.07 | 65.5 | |
| SELFCHECKGPTDetector=Qwen 2.5, Future Context=false2025.07 | 64.4 | |
| DIRECTDetector=Qwen 2.5, Future Context=false2025.07 | 63 | |
| SCDetector=LLaMA 3.1, Future Context=false2025.07 | 62.5 | |
| SCDetector=Gemma 3, Future Context=false2025.07 | 61.1 | |
| SC+fDetector=Qwen 2.5, Future Context=true2025.07 | 59.5 | |
| DIRECT+fDetector=Gemma 3, Future Context=true2025.07 | 58 | |
| DIRECTDetector=Gemma 3, Future Context=false2025.07 | 52.5 | |
| SCDetector=Qwen 2.5, Future Context=false2025.07 | 50.7 |