Question Answering on Natural Questions (Context Relevance, Faithfulness, LLM-as-a-Judge)
80LLM-as-a-Judge ScoreHippoRAG 2
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| HippoRAG 2LLM=Qwen2.5 7B2026.05 | 80 | — | — | |
| PAI-2LLM=Qwen2.5 7B, Retrieval Mode=Combined Retrieval (best), Plan Enhancement=true, Algorithm Config=BS+NR / E2026.05 | 69 | 93 | 91 | |
| PAI-2LLM=Qwen2.5 7B, Retrieval Mode=only Traversal Algorithms, Plan Enhancement=true2026.05 | 67 | 91 | 93 | |
| RAPTORLLM=Qwen2.5 7B2026.05 | 66 | — | — | |
| PAI-2LLM=Qwen2.5 7B, Retrieval Mode=only Naive Retriever, Plan Enhancement=true2026.05 | 64 | 88 | 96 | |
| PAI-2LLM=Qwen2.5 7B, Retrieval Mode=only Traversal Algorithms, Plan Enhancement=false2026.05 | 57 | — | — | |
| PAI-1LLM=Qwen2.5 7B, Retrieval Mode=only Naive Retriever2026.05 | 56 | 68 | 63 | |
| PAI-1LLM=Qwen2.5 7B, Retrieval Mode=Combined Retrieval (best), Algorithm Config=BS+NR / E2026.05 | 56 | — | — | |
| PAI-1LLM=Qwen2.5 7B, Retrieval Mode=only Traversal Algorithms2026.05 | 55 | 68 | 61 | |
| LightRAGLLM=Qwen2.5 7B2026.05 | 26 | — | — |