CrossCult-KIBench: A Benchmark for Cross-Cultural Knowledge Insertion in MLLMs

概要

arXiv:2605.06115v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs), trained primarily on English-centric data, frequently generate culturally inappropriate or misaligned responses in cross-cultural settings. To mitigate this, we introduce the task of cross-cultural knowledge i…