Long-form QA on LiveQA (test)
27.33ROUGE-1GPT-4o + MedBioRAG
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| GPT-4o + MedBioRAGFine-tuned=false, MedBioRAG=true2025.12 | 27.33 | 6.39 | 13.42 | 15.29 | -1.6 | -29.99 | |
| GPT-4oFine-tuned=false, MedBioRAG=false2025.12 | 26.96 | 5.8 | 13.42 | 1.41 | -2.93 | -34.79 | |
| Fine-Tuned GPT-4oFine-tuned=true, MedBioRAG=false2025.12 | 24.12 | 6.18 | 13.31 | 1.63 | 1.1 | -46.48 | |
| Fine-Tuned GPT-4o + MedBioRAGFine-tuned=true, MedBioRAG=true2025.12 | 15.73 | 4.58 | 10.74 | 1.2 | 2.29 | -86.99 |