Factoid Question Answering on BioASQ Task B
55.05Strict ScoreGPT4-Turbo
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GPT4-TurboGenerator=GPT4-Turbo, Retriever=None2025.10 | 55.05 | 65.15 | 60.1 | |
| ParallaxRAG + Qwen3-PlusGenerator=Qwen3-Plus, Retriever=ParallaxRAG2025.10 | 42.1 | 82.22 | 86.67 | |
| Single-View + Qwen3-PlusGenerator=Qwen3-Plus, Retriever=Single-View2025.10 | 37.73 | 72.14 | 84.62 | |
| GPT-4oGenerator=GPT-4o, Retriever=None2025.10 | 34.62 | 34.62 | 34.62 | |
| Qwen3-PlusGenerator=Qwen3-Plus, Retriever=None2025.10 | 32.19 | 62.13 | 41.32 | |
| Deepseek-R1-8BGenerator=Deepseek-R1-8B, Retriever=None2025.10 | 26.2 | 27.33 | 26.77 |