Ensembling Multiple Hallucination Detectors Trained on VLLM Internal Representations

Yuto Nakamizo, Ryuhei Miyazato, Hikaru Tanabe +2

This paper presents the 5th place solution by our team, y3h2, for the Meta CRAG-MM Challenge at KDD Cup 2025. The CRAG-MM benchmark is a visual question answering (VQA) dataset foc…