Multi-hop Question Answering on CofCA
45.3EMSARDI
Evaluation results
| Method | Links | |
|---|---|---|
| SARDITraining Paradigm=Training-free, Backbone=DREAM-7B, Retrieval Strategy=SARDI, Diffusion Threshold (tau_c)=0.92026.06 | 45.3 | |
| SARDITraining Paradigm=Training-free, Backbone=DREAM-7B, Retrieval Strategy=SARDI, Diffusion Threshold (tau_c)=0.952026.06 | 44.9 | |
| Search-R1Training Paradigm=RL-trained, Backbone=Qwen2.5-7B2026.06 | 44.4 | |
| DLM W/ RET@STATICTraining Paradigm=Training-free, Backbone=DREAM-7B, Retrieval Strategy=STATIC, Diffusion Threshold (tau_c)=0.92026.06 | 43.4 | |
| ReActTraining Paradigm=Training-free, Backbone=Qwen2.5-7B2026.06 | 42.9 | |
| AR W/ RET@1Training Paradigm=Training-free, Backbone=Qwen2.5-7B, Retrieval Strategy=RET@12026.06 | 41.2 | |
| AR W/ RET@STATICTraining Paradigm=Training-free, Backbone=Qwen2.5-7B, Retrieval Strategy=STATIC2026.06 | 41 | |
| AR W/ RET@10Training Paradigm=Training-free, Backbone=Qwen2.5-7B, Retrieval Strategy=RET@102026.06 | 39.6 | |
| AdaptiveRAGTraining Paradigm=Training-free, Backbone=Qwen2.5-7B2026.06 | 38.4 | |
| AR W/ RET@ADAPTIVETraining Paradigm=Training-free, Backbone=Qwen2.5-7B, Retrieval Strategy=ADAPTIVE2026.06 | 32.4 |