Long-horizon legal inquiry on Taiwanese criminal case Abstract (Case C)
98.6CompletenessSoft-FSM
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Soft-FSMvariant=V32026.02 | 98.6 | 0 | 4 | |
| Pure LLMvariant=V12026.02 | 35.8 | 0.9 | 60.5 | |
| Stage Promptvariant=V22026.02 | 20.5 | 66.2 | 24 |
| Method | Links | |||
|---|---|---|---|---|
| Soft-FSMvariant=V32026.02 | 98.6 | 0 | 4 | |
| Pure LLMvariant=V12026.02 | 35.8 | 0.9 | 60.5 | |
| Stage Promptvariant=V22026.02 | 20.5 | 66.2 | 24 |