Question Answering on PopQA (F1 score)
43.31F1 ScoreGPT-4o (2024-11-20)
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o (2024-11-20)Version=2024-11-202025.08 | 43.31 | |
| Llama + LoRRBackbone=Llama3.2-3B, Optimization=LoRR2025.08 | 20.02 | |
| Llama + DPOBackbone=Llama3.2-3B, Optimization=DPO2025.08 | 19.51 | |
| Qwen + LoRRBackbone=Qwen2.5-3B, Optimization=LoRR2025.08 | 17.4 | |
| Qwen (Base)Backbone=Qwen2.5-3B, Mode=Base2025.08 | 17.17 | |
| Qwen + DPOBackbone=Qwen2.5-3B, Optimization=DPO2025.08 | 17.02 | |
| Llama (Base)Backbone=Llama3.2-3B, Mode=Base2025.08 | 15.9 |