Issues-in-dispute ranking on LexIssue (out-of-domain)
78.46RecallQwen3-8B-PD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen3-8B-PDEvaluation protocol=prompt2026.06 | 78.46 | 87.63 | |
| GPT-4Evaluation protocol=prompt2026.06 | 77.8 | 87.12 | |
| DeepSeek-R1Evaluation protocol=prompt2026.06 | 76.46 | 85.94 | |
| Qwen3-8B-JEvaluation protocol=prompt2026.06 | 76.26 | 86.47 | |
| GPT-4Evaluation protocol=one-shot2026.06 | 76.12 | 86.29 | |
| Qwen3-8BEvaluation protocol=prompt2026.06 | 74.78 | 84.02 | |
| Qwen-3.5-27BEvaluation protocol=prompt2026.06 | 72.56 | 84.42 | |
| Qwen3-4B-JEvaluation protocol=prompt2026.06 | 71.26 | 80.35 | |
| Qwen3-8B-JEvaluation protocol=one-shot2026.06 | 70.68 | 81.73 | |
| Qwen3-8BEvaluation protocol=one-shot2026.06 | 70.55 | 81.2 | |
| Qwen3-4B-PDEvaluation protocol=one-shot2026.06 | 70.45 | 80.73 | |
| Qwen3-8B-PDEvaluation protocol=one-shot2026.06 | 70.23 | 81.61 | |
| Qwen3-4B-PDEvaluation protocol=prompt2026.06 | 70.15 | 80.63 | |
| Qwen-3.5-27BEvaluation protocol=one-shot2026.06 | 69.75 | 81.16 | |
| Qwen3-4BEvaluation protocol=one-shot2026.06 | 68.51 | 78.73 | |
| Qwen3-4B-JEvaluation protocol=one-shot2026.06 | 67.21 | 77.73 | |
| Qwen3-4BEvaluation protocol=prompt2026.06 | 66.65 | 76.87 | |
| DeepSeek-R1Evaluation protocol=one-shot2026.06 | 65.46 | 77.63 | |
| Qwen2.5-7B-InstructEvaluation protocol=prompt2026.06 | 38.2 | 43.63 | |
| Qwen2.5-7B-InstructEvaluation protocol=one-shot2026.06 | 36.36 | 40.5 |