Question Answering on FACTS
46.59F1 ScoreGPT-4o (2024-11-20)
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o (2024-11-20)Version=2024-11-202025.08 | 46.59 | |
| Llama + LoRRBackbone=Llama3.2-3B, Optimization=LoRR2025.08 | 21.61 | |
| Llama + DPOBackbone=Llama3.2-3B, Optimization=DPO2025.08 | 21.09 | |
| Qwen + LoRRBackbone=Qwen2.5-3B, Optimization=LoRR2025.08 | 18.57 | |
| Qwen (Base)Backbone=Qwen2.5-3B, Mode=Base2025.08 | 18.52 | |
| Qwen + DPOBackbone=Qwen2.5-3B, Optimization=DPO2025.08 | 18.26 | |
| Llama (Base)Backbone=Llama3.2-3B, Mode=Base2025.08 | 17.11 |