Sequence Summarization on CLPsych Step 4 2026 (test)
76.3ConsistencyBaseline
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| BaselinePrompting=zero-shot2026.06 | 76.3 | 75.3 | 25.5 | |
| Qwen3.5-4BModel=Qwen3.5-4B, Task Stage=Step 42026.06 | 66.9 | 85.7 | 29 | |
| Qwen3-4BModel=Qwen3-4B, Task Stage=Step 42026.06 | 65.4 | 83.4 | 28.4 |