Medical Long-form Answering on ExpertQA Biomed
3.7RelevanceOriginal Question
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Original QuestionReader=Frozen Qwen2.5-7B2025.01 | 3.7 | 3.6 | 3.6 | 3.7 | |
| No RetrievalReader=Frozen Qwen2.5-7B2025.01 | 3.6 | 3.4 | 2.7 | — | |
| SERTSReader=Frozen Qwen2.5-7B2025.01 | 3.6 | 3.3 | 2.7 | 3.1 | |
| SPO PlanningReader=Frozen Qwen2.5-7B2025.01 | 3.6 | 4.3 | 4.1 | 4 |