Question Answering on LV-Eval (test)
14.5EMSearch-R1
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Search-R1LLM Generator=Qwen2.5-7B-Instruct2026.02 | 14.5 | 18.5 | |
| s3LLM Generator=Qwen2.5-7B-Instruct2026.02 | 12.9 | 16.9 | |
| MultiCube-RAGLLM Generator=Qwen2.5-7B-Instruct2026.02 | 12.7 | 16.2 | |
| MultiCube-RAGGenerator=GPT-4o-mini2026.02 | 11.3 | 14.5 | |
| MultiCube-RAGGenerator=Llama3.3-70B-Instruct2026.02 | 11.2 | 14.2 | |
| HippoRAG 2Generator=GPT-4o-mini2026.02 | 10.5 | 14 | |
| HippoRAG 2Generator=Llama3.3-70B-Instruct2026.02 | 9.7 | 12.9 | |
| IRCoTGenerator=GPT-4o-mini2026.02 | 8.9 | 12.3 | |
| NV-Embed-v2 (7B)Generator=GPT-4o-mini2026.02 | 7.3 | 10 | |
| NV-Embed-v2 (7B)Generator=Llama3.3-70B-Instruct2026.02 | 7.3 | 9.8 | |
| BM25Generator=GPT-4o-mini2026.02 | 6.5 | 9.4 | |
| HippoRAGGenerator=Llama3.3-70B-Instruct2026.02 | 6.5 | 8.4 | |
| RAPTORGenerator=GPT-4o-mini2026.02 | 5.6 | 9.2 | |
| RankCoTGenerator=GPT-4o-mini2026.02 | 5.6 | 8.2 | |
| GraphRAGGenerator=GPT-4o-mini2026.02 | 4.9 | 11 | |
| HippoRAGGenerator=GPT-4o-mini2026.02 | 4.8 | 7.6 | |
| GraphRAGGenerator=Llama3.3-70B-Instruct2026.02 | 4.8 | 11.2 | |
| BM25Generator=Llama3.3-70B-Instruct2026.02 | 4 | 5.9 | |
| RAPTORGenerator=Llama3.3-70B-Instruct2026.02 | 2.4 | 5 |