Hallucination Detection on Dolly-15k Qwen2.5-3B (test)
80.55PrecisionLRP4RAG_LLM
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| LRP4RAG_LLM2026.01 | 80.55 | 82.91 | 81.71 | |
| SEP2026.01 | 77.94 | 79.19 | 78.56 | |
| SIRG2026.01 | 72.1 | 95.49 | 82.17 | |
| EigenScore2026.01 | 68.88 | 64.58 | 66.66 | |
| SelfCheckGPT2026.01 | 67.32 | 32.47 | 43.88 | |
| Prompt2026.01 | 58.41 | 24.98 | 34.99 |