Vision-Language Models (VLMs) such as GPT-4V have recently demonstrated
incredible strides on diverse vision language tasks. We dig into vision-based
deductive reasoning, a more sophisticated but less explored realm, and find
previously unexposed blindspots in the current SOTA VLMs. Specifically, we
leverage Raven's Progressive Matrices (RPMs), to assess VLMs' abilities to
perform multi-hop relational and deductive reasoning relying solely on visual
clues. We perform comprehensive evaluations of several popular VLMs employing
standard strategies such as in-context learning, self-consistency, and
Chain-of-thoughts (CoT) on three diverse datasets, including the Mensa IQ test,
IntelligenceTest, and RAVEN. The results reveal that despite the impressive
capabilities of LLMs in text-based reasoning, we are still far from achieving
comparable proficiency in visual deductive reasoning. We found that certain
standard strategies that are effective when applied to LLMs do not seamlessly
translate to the challenges presented by visual reasoning tasks. Moreover, a
detailed analysis reveals that VLMs struggle to solve these tasks mainly
because they are unable to perceive and comprehend multiple, confounding
abstract patterns in RPM examples.

近期，Vision-Language Models (VLMs) 取得了惊人的进展，但在基于视觉的演绎推理方面仍存在尚未发现的局限性。采用 Raven's Progressive Matrices (RPMs) 测试了几种热门的 VLMs 的能力，结果表明，虽然 VLMs 在文本推理方面表现出色，但在视觉演绎推理方面还有很大提升空间。详细分析揭示出 VLMs 在解决这些任务时主要困难在于无法感知和理解 RPM 示例中的多个、混淆的抽象模式。