Question Answering on DiaASQ
35LLM-as-a-Judge ScorePAI-1
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| PAI-1LLM=Qwen2.5 7B, Retrieval Mode=only Traversal Algorithms2026.05 | 35 | 63 | 36 | |
| PAI-1LLM=Qwen2.5 7B, Retrieval Mode=Combined Retrieval (best), Algorithm Config=BS+WC / all2026.05 | 35 | 63 | 36 | |
| PAI-2LLM=Qwen2.5 7B, Retrieval Mode=only Traversal Algorithms, Plan Enhancement=true2026.05 | 34 | 83 | 58 | |
| PAI-2LLM=Qwen2.5 7B, Retrieval Mode=Combined Retrieval (best), Plan Enhancement=true, Algorithm Config=BS+WC / E2026.05 | 34 | 83 | 57 | |
| HippoRAG 2LLM=Qwen2.5 7B2026.05 | 28 | — | — | |
| PAI-2LLM=Qwen2.5 7B, Retrieval Mode=only Traversal Algorithms, Plan Enhancement=false2026.05 | 26 | 83 | 63 | |
| PAI-2LLM=Qwen2.5 7B, Retrieval Mode=only Naive Retriever, Plan Enhancement=true2026.05 | 26 | 66 | 60 | |
| RAPTORLLM=Qwen2.5 7B2026.05 | 15 | — | — | |
| PAI-1LLM=Qwen2.5 7B, Retrieval Mode=only Naive Retriever2026.05 | 14 | — | — | |
| LightRAGLLM=Qwen2.5 7B2026.05 | 7 | — | — |