Multi-hop Question Answering on 2Wiki (top-5 accuracy)
84.2Top-5 AccuracyMoG-IRCoT
Evaluation results
| Method | Links | |
|---|---|---|
| MoG-IRCoTBase LLM=GPT-4o-mini, Evaluation protocol=top-5 accuracy, Reasoning Strategy=IRCoT2026.05 | 84.2 | |
| MoGBase LLM=GPT-4o-mini, Evaluation protocol=top-5 accuracy2026.05 | 79.8 | |
| LinearRAGBase LLM=GPT-4o-mini, Evaluation protocol=top-5 accuracy2026.05 | 63.7 | |
| Youtu-GraphRAG-IRCoTBase LLM=GPT-4o-mini, Evaluation protocol=top-5 accuracy, Reasoning Strategy=IRCoT2026.05 | 58.1 | |
| GFM-RAGBase LLM=GPT-4o-mini, Evaluation protocol=top-5 accuracy2026.05 | 56.8 | |
| Youtu-GraphRAGBase LLM=GPT-4o-mini, Evaluation protocol=top-5 accuracy2026.05 | 55.4 | |
| HippoRAG2Base LLM=GPT-4o-mini, Evaluation protocol=top-5 accuracy2026.05 | 55 | |
| HippoRAGBase LLM=GPT-4o-mini, Evaluation protocol=top-5 accuracy2026.05 | 53.2 | |
| E2GraphRAGBase LLM=GPT-4o-mini, Evaluation protocol=top-5 accuracy2026.05 | 49.8 | |
| RAPTORBase LLM=GPT-4o-mini, Evaluation protocol=top-5 accuracy2026.05 | 43.9 | |
| LightRAGBase LLM=GPT-4o-mini, Evaluation protocol=top-5 accuracy2026.05 | 43.3 | |
| G-retrieverBase LLM=GPT-4o-mini, Evaluation protocol=top-5 accuracy2026.05 | 25.7 |