Puzzled by Puzzles: When Vision-Language Models Can't Take a Hint

TL;DR

This paper evaluates how well current vision-language models interpret rebus puzzles, revealing their strengths in simple clues but significant struggles with abstract reasoning and visual metaphors.

Contribution

It introduces a new benchmark of diverse rebus puzzles and analyzes VLMs' performance, highlighting their limitations in complex multi-modal reasoning tasks.

Findings

VLMs perform well on simple visual clues

Struggle with abstract reasoning and metaphors

Benchmark reveals gaps in current models' capabilities

Abstract

Rebus puzzles, visual riddles that encode language through imagery, spatial arrangement, and symbolic substitution, pose a unique challenge to current vision-language models (VLMs). Unlike traditional image captioning or question answering tasks, rebus solving requires multi-modal abstraction, symbolic reasoning, and a grasp of cultural, phonetic and linguistic puns. In this paper, we investigate the capacity of contemporary VLMs to interpret and solve rebus puzzles by constructing a hand-generated and annotated benchmark of diverse English-language rebus puzzles, ranging from simple pictographic substitutions to spatially-dependent cues ("head" over "heels"). We analyze how different VLMs perform, and our findings reveal that while VLMs exhibit some surprising capabilities in decoding simple visual clues, they struggle significantly with tasks requiring abstract reasoning, lateral thinking, and understanding visual metaphors.