Question Answering on 2Wiki 500 samples (val)
39.6EMASSISTRAG
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| ASSISTRAGMain LLM=ChatGPT3.5, Retrieval Setting=Baselines with retrieval2024.11 | 39.6 | 45.6 | 45.7 | |
| ASSISTRAGMain LLM=ChatGLM3 6B, Retrieval Setting=Baselines with retrieval2024.11 | 38 | 43.2 | 42.8 | |
| ASSISTRAGMain LLM=LLaMA2-chat 7B, Retrieval Setting=Baselines with retrieval2024.11 | 36.2 | 41 | 40.3 | |
| SELF-RAGMain LLM=SELF-RAG 7B, Retrieval Setting=Baselines with retrieval2024.11 | 35 | 40.7 | 41 | |
| IRCoTMain LLM=ChatGPT3.5, Retrieval Setting=Baselines with retrieval2024.11 | 30.8 | 42.6 | 42.3 | |
| LLMLinguaMain LLM=ChatGPT3.5, Retrieval Setting=Baselines with retrieval2024.11 | 29.4 | 38.6 | 37.8 | |
| Self-AskMain LLM=ChatGPT3.5, Retrieval Setting=Baselines with retrieval2024.11 | 28.6 | 37.5 | 42.8 | |
| ReActMain LLM=ChatGPT3.5, Retrieval Setting=Baselines with retrieval2024.11 | 25 | 33 | 31.6 | |
| Naive RAGMain LLM=ChatGPT3.5, Retrieval Setting=Baselines with retrieval2024.11 | 23.8 | 30.2 | 31.1 | |
| CloseBookMain LLM=ChatGPT3.5, Retrieval Setting=Baselines without retrieval2024.11 | 21.6 | 25.7 | 24.5 | |
| Naive RAGMain LLM=ChatGLM3 6B, Retrieval Setting=Baselines with retrieval2024.11 | 17.8 | 25 | 25.2 | |
| Naive RAGMain LLM=LLaMA2-chat 7B, Retrieval Setting=Baselines with retrieval2024.11 | 17.4 | 23.7 | 22.8 | |
| CloseBookMain LLM=ChatGLM3 6B, Retrieval Setting=Baselines without retrieval2024.11 | 15.8 | 19.5 | 20 | |
| CloseBookMain LLM=LLaMA2-chat 7B, Retrieval Setting=Baselines without retrieval2024.11 | 14.4 | 18.2 | 17.8 |