Dialog on Wizard of Wikipedia (WoW) (test)
11.38F1 ScoreINFO-RAG
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| INFO-RAGBackbone=LLaMA-2-13B-chat, Zero-shot=true2024.02 | 11.38 | 46.55 | |
| LLaMA-2-13B-chatZero-shot=true2024.02 | 11.19 | 43.23 | |
| INFO-RAGBackbone=LLaMA-2-7B-chat, Zero-shot=true2024.02 | 10.49 | 43.78 | |
| LLaMA-2-7B-chatZero-shot=true2024.02 | 10.21 | 40.83 | |
| INFO-RAGBackbone=LLaMA-2-7B, Zero-shot=true2024.02 | 9.09 | 39.83 | |
| LLaMA-2-7BZero-shot=true2024.02 | 7.85 | 35.78 | |
| INFO-RAGBackbone=LLaMA-2-13B, Zero-shot=true2024.02 | 7.2 | 41.04 | |
| LLaMA-2-13BZero-shot=true2024.02 | 7.04 | 36.86 |