Issues-in-dispute ranking on LexIssue (in-domain)
83.14RecallQwen3-8B-PD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen3-8B-PDEvaluation protocol=prompt2026.06 | 83.14 | 90.43 | |
| Qwen3-8B-JEvaluation protocol=prompt2026.06 | 81.46 | 88.85 | |
| GPT-4Evaluation protocol=prompt2026.06 | 80.92 | 89.18 | |
| GPT-4Evaluation protocol=one-shot2026.06 | 80.07 | 89.14 | |
| DeepSeek-R1Evaluation protocol=prompt2026.06 | 78.82 | 87.52 | |
| Qwen-3.5-27BEvaluation protocol=prompt2026.06 | 77.75 | 87.19 | |
| Qwen3-8BEvaluation protocol=prompt2026.06 | 76.94 | 85.22 | |
| Qwen3-8B-PDEvaluation protocol=one-shot2026.06 | 74.4 | 84.35 | |
| Qwen3-8B-JEvaluation protocol=one-shot2026.06 | 73.4 | 82.54 | |
| Qwen-3.5-27BEvaluation protocol=one-shot2026.06 | 73.11 | 84.59 | |
| Qwen3-4B-PDEvaluation protocol=one-shot2026.06 | 70.75 | 80.78 | |
| Qwen3-8BEvaluation protocol=one-shot2026.06 | 68.99 | 80.55 | |
| Qwen3-4B-PDEvaluation protocol=prompt2026.06 | 68.94 | 78.86 | |
| Qwen3-4B-JEvaluation protocol=prompt2026.06 | 68.65 | 77.4 | |
| Qwen3-4BEvaluation protocol=one-shot2026.06 | 67.98 | 77.57 | |
| DeepSeek-R1Evaluation protocol=one-shot2026.06 | 66.86 | 78.87 | |
| Qwen3-4BEvaluation protocol=prompt2026.06 | 65.95 | 73.92 | |
| Qwen3-4B-JEvaluation protocol=one-shot2026.06 | 65.79 | 75.96 | |
| Qwen2.5-7B-InstructEvaluation protocol=prompt2026.06 | 39.16 | 44.01 | |
| Qwen2.5-7B-InstructEvaluation protocol=one-shot2026.06 | 37.97 | 42.23 |