Object HalBench

Object-HalBench is a multimodal hallucination benchmark used to evaluate the performance of large vision-language models in terms of their tendency to generate hallucinations.

Papers using Object HalBench (3)

Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization2025AdaViP: Aligning Multi-modal LLMs via Adaptive Vision-enhanced Preference Optimization2025DAMA: Data- and Model-aware Alignment of Multi-modal LLMs2025