Article Prediction on CAIL
43Public Safety AccuracyLegalGraphRAG
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| LegalGraphRAGSize=8B-Inst2026.05 | 43 | 64.9 | 37.8 | 61 | 44.6 | 69.4 | 54.5 | 70.6 | 47.9 | — | |
| DeepSeek-V3.1Size=∼200B2026.05 | 42.3 | 63.2 | 37.1 | 61.3 | 44.5 | 68.8 | 51.9 | 67.3 | 44.9 | 3 | |
| ADAPTSize=7B-Inst2026.05 | 40.1 | 50.8 | 31.6 | 42.4 | 39.6 | 54.9 | 41 | 50.5 | 41.3 | 6.6 | |
| DISC-LawLLM-7BSize=7B-Inst2026.05 | 36.5 | 55.9 | 29.9 | 48.8 | 41.5 | 61.2 | 39.3 | 57.8 | 38.2 | 9.7 | |
| RAPTORSize=8B-Inst2026.05 | 36.4 | 59.2 | 33.4 | 53.9 | 38.9 | 64.1 | 41 | 61.7 | 37.2 | 10.7 | |
| HippoRAG2Size=8B-Inst2026.05 | 35.2 | 60.3 | 33.1 | 53.7 | 41.7 | 67 | 42.6 | 63.8 | 39.8 | 8.1 | |
| Legal ∆Size=7B-Inst2026.05 | 33 | 54.9 | 27.8 | 51 | 34.6 | 59.4 | 44.5 | 60.6 | 37.9 | 10 | |
| Naive RAGSize=8B-Inst2026.05 | 30.4 | 45.7 | 29.2 | 48.6 | 37.5 | 54.1 | 36.6 | 51.1 | 34.8 | 13.1 | |
| Qwen-2.5-7B-InstructSize=7B-Inst2026.05 | 28.7 | 53.8 | 24.1 | 48.2 | 26.6 | 53.5 | 36 | 56.2 | 30.1 | 17.8 | |
| Internlm3-8b-instructSize=8B-Inst2026.05 | 27.6 | 59.9 | 26.4 | 52.8 | 30.8 | 59 | 33.6 | 57.6 | 29.9 | 18 | |
| GPT-4o-miniSize=∼8B2026.05 | 24.7 | 57.2 | 25.7 | 42.4 | 24.6 | 51.8 | 34.7 | 55 | 30.9 | 17 | |
| Qwen-3-8BSize=8B-Inst2026.05 | 23.9 | 58.5 | 27.6 | 51.2 | 36.6 | 62.2 | 46.2 | 66.7 | 35.9 | 12 | |
| Glm-4-9b-chatSize=9B-Inst2026.05 | 23.9 | 60.1 | 25.6 | 51 | 34.7 | 59.4 | 35.1 | 58.5 | 30.8 | 17.1 |