List your company

Hallucination Detection on PUGG

84.3F1 ScoreKG-Guard
46.8656.5866.376.02May 29, 2026

Evaluation results

MethodLinks
KG-GuardGraph encoder=GraphTransformer2026.0584.3
Most Frequent2026.0583.5
KG-GuardGraph encoder=GAT2026.0582.7
GPT 5 MiniInput modalities=G2026.0582.6
GPT 5 MiniInput modalities=G+RS+RT2026.0581.2
SelfCheckNumber of samples=102026.0573.8
Llama 4 ScoutInput modalities=G2026.0568.8
Llama 4 ScoutInput modalities=G+RS2026.0561.3
Llama 4 ScoutInput modalities=G+RS+RT2026.0560.8
Random2026.0558.8
SelfCheckNumber of samples=52026.0548.3