Legal Concept Entailment on Legal Concept Entailment (test)
75.03AccuracyATRIE
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| ATRIEModel=Qwen2.5 (72B)2025.01 | 75.03 | 73.21 | 69.97 | 70.87 | 5.946 | |
| ATRIEModel=Qwen2.5 (14B)2025.01 | 74.5 | 72.49 | 69.56 | 70.39 | 5.84 | |
| Direct InterpretationModel=Qwen2.5 (14B)2025.01 | 72.72 | 70.98 | 66.11 | 66.9 | 5.677 | |
| Direct InterpretationModel=Qwen2.5 (72B)2025.01 | 72.35 | 70.03 | 66.43 | 67.18 | 5.642 | |
| Expert InterpretationModel=Qwen2.5 (72B)2025.01 | 72.13 | 70.78 | 64.68 | 65.3 | 5.63 | |
| Judicial InterpretationModel=Qwen2.5 (72B)2025.01 | 72.1 | 69.87 | 65.82 | 66.54 | 5.573 | |
| Chain-of-ThoughtModel=Qwen2.5 (72B)2025.01 | 71.95 | 72.07 | 63.26 | 63.46 | 5.717 | |
| Expert InterpretationModel=Qwen2.5 (14B)2025.01 | 71.95 | 69.85 | 65.31 | 66.01 | 5.581 | |
| Chain-of-ThoughtModel=Qwen2.5 (14B)2025.01 | 71.52 | 73.83 | 61.6 | 61.01 | 5.666 | |
| Zero-ShotModel=Qwen2.5 (72B)2025.01 | 71.38 | 72.64 | 61.81 | 61.42 | 5.658 | |
| Zero-ShotModel=Qwen2.5 (14B)2025.01 | 70.92 | 73.04 | 60.78 | 59.88 | 5.525 | |
| Judicial InterpretationModel=Qwen2.5 (14B)2025.01 | 70.92 | 68.24 | 64.62 | 65.23 | 5.347 | |
| RandomModel=Qwen2.5 (72B)2025.01 | 51.66 | 51.13 | 51.23 | 50.32 | — | |
| RandomModel=Qwen2.5 (14B)2025.01 | 51.66 | 51.13 | 51.23 | 50.32 | — |