Question Answering on HotpotQA (test) (Accuracy Metric)
48.71AccuracyAccurateRAG
Evaluation Results
| Method | Links | |
|---|---|---|
| AccurateRAGLLM Backbone=Llama-3-8B, Fine-tuning=true2025.10 | 48.71 | |
| AccurateRAGLLM Backbone=Llama-2-7B, Fine-tuning=true2025.10 | 45.71 | |
| RankRAGLLM Backbone=Llama-3-8B, Fine-tuning=true2025.10 | 35.3 | |
| RAFTLLM Backbone=Llama-2-7B, Fine-tuning=true, Chain-of-Thought (CoT)=GPT-4 CoT2025.10 | 35.28 | |
| RAFTLLM Backbone=Llama-2-7B, Fine-tuning=true, Chain-of-Thought (CoT)=false2025.10 | 25.62 |