List your company

Hallucination Detection on CWQ

87.4F1 ScoreKG-Guard
57.13664.99372.8580.707May 29, 2026

Evaluation results

MethodLinks
KG-GuardGraph encoder=GraphTransformer2026.0587.4
KG-GuardGraph encoder=GAT2026.0586.3
GPT 5 MiniInput modalities=G+RS+RT2026.0584.2
Most Frequent2026.0583.5
GPT 5 MiniInput modalities=G2026.0582.6
SelfCheckNumber of samples=102026.0572.2
SelfCheckNumber of samples=52026.0567.1
Llama 4 ScoutInput modalities=G+RS2026.0561.3
Llama 4 ScoutInput modalities=G+RS+RT2026.0561.2
Llama 4 ScoutInput modalities=G2026.0560.2
Random2026.0558.3