Hallucination Detection on Dolly-15k Qwen2.5-7B (test)
84.21PrecisionSIRG
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SIRG2026.01 | 84.21 | 96 | 89.71 | |
| LRP4RAG_LLM2026.01 | 79.6 | 82.2 | 80.8 | |
| SEP2026.01 | 76.36 | 77.59 | 76.97 | |
| SelfCheckGPT2026.01 | 67.32 | 32.47 | 43.88 | |
| Prompt2026.01 | 61.46 | 47.23 | 53.36 | |
| EigenScore2026.01 | 58.57 | 70.03 | 63.79 |