List your company

Question Answering on CWQ (Acc, F1)

23.62AccuracyGraph-S^3
-0.79925.540411.8818.2196Oct 1, 2025

Evaluation results

MethodLinks
Graph-S^3Generator=Finetuned-7B2025.1023.6230.44—
G-retrieverGenerator=Finetuned-7B2025.1022.6828.38—
RAG/1hopGenerator=Finetuned-7B2025.1019.8526.01—
Graph-S^3Generator=Qwen2-7B2025.1017.8723.29—
Graph-S^3Generator=Llama3-8B2025.1017.1121.17—
LightRAGGenerator=Qwen2-7B2025.1016.223.09—
KG-AgentGenerator=Qwen2-7B2025.1015.6422.45—
G-retrieverGenerator=Qwen2-7B2025.1015.3818.62—
G-retrieverGenerator=Llama3-8B2025.1013.9117.47—
RAG/1hopGenerator=Llama3-8B2025.1013.8517.26—
LightRAGGenerator=Finetuned-7B2025.1013.8519.96—
KG-AgentGenerator=Finetuned-7B2025.1013.7716.29—
RAG/1hopGenerator=Qwen2-7B2025.1012.5516.18—
KG-AgentGenerator=Llama3-8B2025.1010.8213.75—
No graphGenerator=Finetuned-7B2025.1010.1712.31—
No graphGenerator=Llama3-8B2025.109.411.58—
RAG/2hopGenerator=Finetuned-7B2025.108.8914.56—
ToGGenerator=Llama3-8B2025.108.4212.33—
LightRAGGenerator=Llama3-8B2025.108.3315.01—
ToGGenerator=Finetuned-7B2025.107.549.79—
ToGGenerator=Qwen2-7B2025.107.019.61—
RAG/2hopGenerator=Qwen2-7B2025.10710.55—
RAG/2hopGenerator=Llama3-8B2025.106.2910.68—
No graphGenerator=Qwen2-7B2025.106.267.35—
RAG/3hopGenerator=Qwen2-7B2025.100.993.12—
RAG/3hopGenerator=Finetuned-7B2025.100.934.36—
No retrieverGenerator=Finetuned-7B2025.100.681.76—
RAG/3hopGenerator=Llama3-8B2025.100.653.43—
No retrieverGenerator=Qwen2-7B2025.100.371.29—
No retrieverGenerator=Llama3-8B2025.100.141.29—
ReGradModel=LLaMA-3.2 1B, Top-1000 setting=True2026.06——47.18
ReGradModel=LLaMA-3.2 3B, Top-1000 setting=True2026.06——52.57
ReGradModel=LLaMA-3.1 8B, Top-1000 setting=True2026.06——56.41
ReGrad + ICLModel=LLaMA-3.2 1B, Top-1000 setting=True2026.06——50.34
ReGrad + ICLModel=LLaMA-3.2 3B, Top-1000 setting=True2026.06——54.08
ReGrad + ICLModel=LLaMA-3.1 8B, Top-1000 setting=True2026.06——57.52