List your company
ResearchFormerly WizWand

Knowledge Base Question Answering on WebQSP

96Hits@1Logits-to-Logic
41.472855.628969.78583.9411Nov 11, 2025Dec 6, 2025Jan 1, 2026Jan 27, 2026Feb 21, 2026Mar 19, 2026Apr 14, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Logits-to-LogicModel Scale Category=13b model, Backbone=LLaMA3-13b2025.1196——75.2—
Logits-to-LogicModel Scale Category=7-8b model, Backbone=LLaMA3-8b2025.1195.4——63.3—
KG-ReasonerSize=30B, Methodology=KG + LLM with Fine-Tuning (LLM Backbone Fine-Tuning)2026.0493.15————
GCRModel Category=Hybrid System, Backbone=LLaMA3-8b+ChatGPT2025.1192.6——73.2—
GCRModel Category=Hybrid System, Backbone=LLaMA3-8b+GPT4o-mini2025.1192.2——74.1—
RoGModel Scale Category=13b model, Backbone=LLaMA3-13b2025.1189.1——73.6—
STARSetting=Lightweight Retriever, RT=0.92026.0488.7——74.1—
RD-PSetting=Lightweight Retriever, RT=0.82026.0488.1——73.1—
PoG with GPT-4Methodology=KG + LLMs w/o Fine-Tuning2026.0487.3————
RoGSetting=LLM-centric Retriever, RT=1.62026.0487.1——71.6—
RoGSize=7B, Methodology=KG + LLM with Fine-Tuning (LLM Backbone Fine-Tuning)2026.0485.7————
RoGModel Scale Category=7-8b model, Backbone=LLaMA2-Chat-7B2025.1185.7——70.8—
Graph CoTSetting=LLM-centric Retriever, RT=123.32026.0485.3——73.5—
KG-CoT with GPT 4Methodology=KG + LLM with Fine-Tuning (Small Models Fine-Tuning)2026.0484.9————
GPT-4o-mini + KGMethodology=KG + LLMs w/o Fine-Tuning2026.0484.4————
LightPROF (LLaMA3-8B)Size=8B, Methodology=KG + LLM with Fine-Tuning (Small Models Fine-Tuning)2026.0483.8————
KG-AgentMethodology=KG + LLM with Fine-Tuning (LLM Backbone Fine-Tuning)2026.0483.3————
ToG with GPT 4Methodology=KG + LLMs w/o Fine-Tuning2026.0482.6————
LLaMA-3.3-70B + KGSize=70B, Methodology=KG + LLMs w/o Fine-Tuning2026.0481.9————
DeepSeek-R1-Distill-Llama-70B + KGSize=70B, Methodology=KG + LLMs w/o Fine-Tuning2026.0481.34————
SubgraphRAGModel Scale Category=7-8b model, Backbone=Llama3.1-8B2025.1181.2——67.9—
GNN-RAGModel Category=Hybrid System, Backbone=LLaMA2-7b+GNN2025.1180.6——71.3—
Readi with GPT-4Methodology=KG + LLMs w/o Fine-Tuning2026.0478.7————
Chain-of-QuestionMethodology=KG + LLM with Fine-Tuning (Small Models Fine-Tuning)2026.0478.1————
DeepSeek-R1-Distill-Llama-70BSize=70B, Methodology=LLM w/o KG2026.0477.43————
DeepSeek-R1-70BSetting=LLM without KG, RT=16.32026.0475.2——59—
Qwen-2.5-7B (SFT) + KGSize=7B, Methodology=KG + LLM with Fine-Tuning (LLM Backbone Fine-Tuning)2026.0474.8————
G-RetrieverSize=7B, Methodology=KG + LLM with Fine-Tuning (LLM Backbone Fine-Tuning)2026.0473.79————
ChatGPT+CoTModel Category=Closed-source business model2025.1173.5——38.5—
LLaMA-3.1-8B (SFT) + KGSize=8B, Methodology=KG + LLM with Fine-Tuning (LLM Backbone Fine-Tuning)2026.0472.98————
Qwen-2.5-7B + KGSize=7B, Methodology=KG + LLMs w/o Fine-Tuning2026.0472.6————
GPT-4oMethodology=LLM w/o KG2026.0472.55————
LLaMA-3.1-8B + KGSize=8B, Methodology=KG + LLMs w/o Fine-Tuning2026.0471.32————
LLaMA-3.3-70BSize=70B, Methodology=LLM w/o KG2026.0471.12————
KD-CoTModel Scale Category=7-8b model, Backbone=LLaMA2-7b2025.1168.6——52.5—
ChatGPT+Few-shotModel Category=Closed-source business model2025.1168.5——38.1—
ToGSetting=LLM-centric Retriever, RT=41.72026.0467.6——61.3—
GPT-4o-miniMethodology=LLM w/o KG2026.0465.97————
G-RetrieverSetting=Lightweight Retriever, RT=8.92026.0463.1——69.3—
Llama3.3-70BSetting=LLM without KG, RT=2.82026.0462.5——43.2—
GRAGSetting=Lightweight Retriever, RT=10.12026.0460.5——52.8—
ChatGPTModel Category=Closed-source business model2025.1159.3——43.5—
DALKSetting=Lightweight Retriever, RT=24.72026.0458.9——50.2—
Qwen2.5-72BSetting=LLM without KG, RT=3.52026.0458.1——39.4—
LLaMA2-7bModel Scale Category=7-8b model2025.1156.4——36.5—
Interactive-KBQAModel Scale Category=13b model, Backbone=LLaMA2-13b2025.1156.2——54.8—
LLaMA3.1-8bModel Scale Category=7-8b model2025.1155.5——34.8—
Interactive-KBQA (13B)Size=13B, Methodology=KG + LLM with Fine-Tuning (LLM Backbone Fine-Tuning)2026.0454.86————
Qwen2-7bModel Scale Category=7-8b model2025.1150.8——35.5—
Qwen-2.5-7BSize=7B, Methodology=LLM w/o KG2026.0446.97————
LLaMA-3.1-8BSize=8B, Methodology=LLM w/o KG2026.0445.07————
Interactive-KBQAModel Scale Category=7-8b model, Backbone=Mistral-7B2025.1145——43.5—
Interactive-KBQA (7B)Size=7B, Methodology=KG + LLM with Fine-Tuning (LLM Backbone Fine-Tuning)2026.0443.57————
CBR-KBQASupervision=Supervised2021.04—73.175.172.869.9
CoT2026.01————62.2
DoG2026.01————91
DP2026.01————87.5
EmbedKGQASupervision=Weakly supervised2021.04———66.6—
FLAREFramework=ToG2026.01————90.4
FLAREFramework=PoG2026.01————93.9
GCR2026.01————92.2
GraftNetSupervision=Weakly supervised2021.04———66.4—
GSRModel Category=Hybrid System, Backbone=T5-3b + LLaMA2-7b2025.11———58.9—
IO Prompt2026.01————63.3
KB-BINDER2026.01————74.4
LATS2026.01————76.5
PathMind2026.01————89.5
PoG2026.01————87.3
ProgRAG2026.01————90.4
PullNetSupervision=Weakly supervised2021.04———68.1—
RAP2026.01————75.6
RoG2026.01————85.7
RwT2026.01————87
SC2026.01————61.1
STAGGSupervision=Supervised2021.04—70.980.371.763.9
T5-11BSupervision=Supervised2021.04—62.162.661.556.5
T5-11B + ReviseSupervision=Supervised2021.04—63.664.36357.7
T5-3BBackbone=T5-3B2022.01———80.7—
T5-baseBackbone=T5-base2022.01———78.83—
T5-largeBackbone=T5-large2022.01———79.45—
ToG2026.01————82.6
ToG 2.02026.01————81.1
ToT2026.01————73.5
Ye et al. (2021b)Extra Pre-training=false2022.01———83.6—