List your company
ResearchFormerly WizWand

Retrieval-Augmented Generation on 2WikiMultiHopQA

65.04F1 ScoreGraph-R1 (ours)
5.29220.803536.31551.8265Jul 29, 2025
Updated 5mo ago

Evaluation results

MethodLinks
Graph-R1 (ours)Backbone=Qwen2.5-7B-Instruct, Knowledge Representation=Graph-based, Learning Strategy=Training2025.0765.0482.42
Graph-R1 (ours)Backbone=Qwen2.5-3B-Instruct, Knowledge Representation=Graph-based, Learning Strategy=Training2025.0757.5676.45
Search-R1Backbone=Qwen2.5-7B-Instruct, Knowledge Representation=Chunk-based, Learning Strategy=Training2025.0741.2970.26
Search-R1Backbone=Qwen2.5-3B-Instruct, Knowledge Representation=Chunk-based, Learning Strategy=Training2025.0738.0454.39
Graph-R1 (ours)Backbone=Qwen2.5-1.5B-Instruct, Knowledge Representation=Graph-based, Learning Strategy=Training2025.0735.1365.73
R1-SearcherBackbone=Qwen2.5-7B-Instruct, Knowledge Representation=Chunk-based, Learning Strategy=Training2025.0733.9669.61
R1Backbone=Qwen2.5-7B-Instruct, Knowledge Representation=Chunk-based, Learning Strategy=Training2025.0730.9959.19
R1Backbone=Qwen2.5-3B-Instruct, Knowledge Representation=Chunk-based, Learning Strategy=Training2025.0728.4556.92
Search-R1Backbone=Qwen2.5-1.5B-Instruct, Knowledge Representation=Chunk-based, Learning Strategy=Training2025.0728.4360.61
R1-SearcherBackbone=Qwen2.5-1.5B-Instruct, Knowledge Representation=Chunk-based, Learning Strategy=Training2025.0728.0158.81
R1Backbone=Qwen2.5-1.5B-Instruct, Knowledge Representation=Chunk-based, Learning Strategy=Training2025.0726.2847.48
R1-SearcherBackbone=Qwen2.5-3B-Instruct, Knowledge Representation=Chunk-based, Learning Strategy=Training2025.0723.555.86
StandardRAGBackbone=GPT-4o-mini, Knowledge Representation=Chunk-based, Learning Strategy=Prompting2025.0722.3173.02
HyperGraphRAGBackbone=GPT-4o-mini, Knowledge Representation=Graph-based, Learning Strategy=Prompting2025.0721.1476.76
SFTBackbone=Qwen2.5-7B-Instruct, Knowledge Representation=Chunk-based, Learning Strategy=Training2025.0720.2863.85
NaiveGenerationBackbone=GPT-4o-mini, Knowledge Interaction=No, Learning Strategy=Prompting2025.0717.0374.86
LightRAGBackbone=GPT-4o-mini, Knowledge Representation=Graph-based, Learning Strategy=Prompting2025.0716.5971.94
HippoRAG2Backbone=GPT-4o-mini, Knowledge Representation=Graph-based, Learning Strategy=Prompting2025.0716.2768.78
GraphRAGBackbone=GPT-4o-mini, Knowledge Representation=Graph-based, Learning Strategy=Prompting2025.0716.0272.81
SFTBackbone=Qwen2.5-1.5B-Instruct, Knowledge Representation=Chunk-based, Learning Strategy=Training2025.0713.2634.72
StandardRAGBackbone=Qwen2.5-7B-Instruct, Knowledge Representation=Chunk-based, Learning Strategy=Prompting2025.0712.7560.06
StandardRAGBackbone=Qwen2.5-3B-Instruct, Knowledge Representation=Chunk-based, Learning Strategy=Prompting2025.0712.5260.01
PathRAGBackbone=GPT-4o-mini, Knowledge Representation=Graph-based, Learning Strategy=Prompting2025.0712.4267.19
SFTBackbone=Qwen2.5-3B-Instruct, Knowledge Representation=Chunk-based, Learning Strategy=Training2025.0712.452.31
NaiveGenerationBackbone=Qwen2.5-7B-Instruct, Knowledge Interaction=No, Learning Strategy=Prompting2025.0712.2566.75
StandardRAGBackbone=Qwen2.5-1.5B-Instruct, Knowledge Representation=Chunk-based, Learning Strategy=Prompting2025.0711.4655.38
NaiveGenerationBackbone=Qwen2.5-1.5B-Instruct, Knowledge Interaction=No, Learning Strategy=Prompting2025.077.7849.13
NaiveGenerationBackbone=Qwen2.5-3B-Instruct, Knowledge Interaction=No, Learning Strategy=Prompting2025.077.5955