Hallucination Detection on SC-Vicuna
71.4AUROCSC+f
Evaluation Results
| Method | Links | |
|---|---|---|
| SC+fDetector=LLaMA 3.1, Future Context=true2025.07 | 71.4 | |
| SELFCHECKGPT+fDetector=LLaMA 3.1, Future Context=true2025.07 | 70.2 | |
| SELFCHECKGPT+fDetector=Gemma 3, Future Context=true2025.07 | 70.1 | |
| SELFCHECKGPTDetector=LLaMA 3.1, Future Context=false2025.07 | 69.6 | |
| DIRECT+fDetector=LLaMA 3.1, Future Context=true2025.07 | 68.4 | |
| DIRECTDetector=LLaMA 3.1, Future Context=false2025.07 | 68 | |
| SELFCHECKGPTDetector=Gemma 3, Future Context=false2025.07 | 67.7 | |
| SC+fDetector=Gemma 3, Future Context=true2025.07 | 67.7 | |
| SCDetector=LLaMA 3.1, Future Context=false2025.07 | 67.3 | |
| SCDetector=Gemma 3, Future Context=false2025.07 | 65.7 | |
| SELFCHECKGPTDetector=Qwen 2.5, Future Context=false2025.07 | 65.7 | |
| DIRECT+fDetector=Qwen 2.5, Future Context=true2025.07 | 65.6 | |
| DIRECTDetector=Qwen 2.5, Future Context=false2025.07 | 65.5 | |
| SELFCHECKGPT+fDetector=Qwen 2.5, Future Context=true2025.07 | 65.1 | |
| SC+fDetector=Qwen 2.5, Future Context=true2025.07 | 60.2 | |
| DIRECT+fDetector=Gemma 3, Future Context=true2025.07 | 57.5 | |
| DIRECTDetector=Gemma 3, Future Context=false2025.07 | 56.6 | |
| SCDetector=Qwen 2.5, Future Context=false2025.07 | 56 |