Jul 2026
MemeBench: What LVLMs Miss When Interpreting Culture-Dependent Memes
KAR, an entity-guided retrieval baseline built on CultureBase is introduced and MemeBench is introduced, a diagnostic benchmark of 1,253 Chinese and English memes with human-written references and quality-controlled VIKR annotations, centered on anime, comics, games, and adjacent online subcultures, to reveal whether an interpretation succeeds, what is missing, and whether targeted evidence fills the diagnosed gap.
Weihang Wang, Kainan Tu, Jielei Zhang et al.
· arXiv.org · 1 citation