A Surprising Failure? Multimodal LLMs and the NLVR Challenge

arXiv:2402.17793v1 Announce Type: cross
Abstract: This study evaluates three state-of-the-art MLLMs -- GPT-4V, Gemini Pro, and the open-source model IDEFICS -- on the compositional natural language vision reasoning task NLVR. Given a human-written sentence paired with a synthetic image, this task requires the model to determine the truth value of the sentence with respect to the image. Despite the strong performance demonstrated by these models, we observe they perform poorly on NLVR, which was constructed to require compositional and spatial …

abstract art arxiv challenge cs.ai cs.cl cs.lg failure gemini gemini pro gpt gpt-4v human image language llms mllms multimodal natural natural language reasoning state study synthetic truth type value vision