Language Modeling on WikiText (test) (ROUGE Evaluation)
64.14ROUGE ScoreINFO-RAG
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| INFO-RAGBackbone=LLaMA-2-13B, Zero-shot=true2024.02 | 64.14 | 41.04 | |
| INFO-RAGBackbone=LLaMA-2-13B-chat, Zero-shot=true2024.02 | 63.92 | 46.55 | |
| INFO-RAGBackbone=LLaMA-2-7B-chat, Zero-shot=true2024.02 | 63.24 | 43.78 | |
| INFO-RAGBackbone=LLaMA-2-7B, Zero-shot=true2024.02 | 62.91 | 39.83 | |
| LLaMA-2-13BZero-shot=true2024.02 | 62.2 | 36.86 | |
| LLaMA-2-7BZero-shot=true2024.02 | 60.77 | 35.78 | |
| LLaMA-2-13B-chatZero-shot=true2024.02 | 60.52 | 43.23 | |
| LLaMA-2-7B-chatZero-shot=true2024.02 | 60.26 | 40.83 |