List your company

Binary safety hallucination detection on PitVQA Open-ended (External val)

91SNNELlama3.2
14.0434.025473.98Nov 3, 2025

Evaluation results

MethodLinks
Llama3.2Evaluation Protocol=Zero-shot2025.119173927479
MedGemma3.0Evaluation Protocol=Zero-shot2025.114873777474
Qwen2.5Evaluation Protocol=Zero-shot2025.114454313029
PitVQAEvaluation Protocol=Zero-shot2025.112793289696
SurgicalGPTEvaluation Protocol=Zero-shot2025.111764668383