Hallucination Detection on RAGTruth Llama2-7B (test)
75.76AccuracyRAGLens
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| RAGLens2025.12 | 75.76 | 0.8413 | 76.36 | |
| LwMLM2025.12 | 69.4 | — | 73.65 | |
| ChainPoll2025.12 | 68.41 | 0.6738 | 70.06 | |
| RAGAS2025.12 | 68.22 | 0.729 | 66.67 | |
| ReDeEP2025.12 | 68.22 | 0.7458 | 71.9 | |
| TurLens2025.12 | 68.21 | 0.651 | 66.58 | |
| Prompt2025.12 | 67 | — | 67.2 | |
| RefCheck2025.12 | 64.67 | 0.6912 | 67.36 | |
| Llama2-13B(LR)classifier=Logistic Regression, features=Llama2-13B2025.12 | 63.5 | — | 65.72 | |
| SEP2025.12 | 61.87 | 0.7143 | 70.48 | |
| SelfCheckGPT2025.12 | 58.44 | — | 46.42 | |
| ITI2025.12 | 56.67 | 0.6714 | 64.96 | |
| P(True)2025.12 | 56.48 | 0.7093 | 65.49 | |
| LN-Entropy2025.12 | 56.2 | 0.5912 | 68.5 | |
| Focus2025.12 | 55.33 | 0.6233 | 65.22 | |
| EigenScore2025.12 | 54.22 | 0.6045 | 66.82 | |
| FAcTScore2025.12 | 53.33 | 0.5428 | 67.19 | |
| Perplexity2025.12 | 53.33 | 0.5091 | 67.49 | |
| SAPLMA2025.12 | 51.55 | 0.7107 | 65.02 | |
| Energy2025.12 | 50.88 | 0.5619 | 66.57 | |
| FactCC2025.12 | 50.22 | 0.4976 | 45.89 |