Benchmarking VLMs' Reasoning About Persuasive Atypical Images
This work addresses a domain-specific gap in evaluating VLMs for rhetorical and persuasive visual media, which is incremental as it introduces new benchmarking tasks but does not propose a novel method.
The paper tackled the problem of vision language models' (VLMs) limited ability to comprehend persuasive atypical images in advertisements, such as surprising object juxtapositions, and found that VLMs lack advanced reasoning capabilities compared to large language models (LLMs), but simple strategies can extract atypicality-aware information for better understanding.
Vision language models (VLMs) have shown strong zero-shot generalization across various tasks, especially when integrated with large language models (LLMs). However, their ability to comprehend rhetorical and persuasive visual media, such as advertisements, remains understudied. Ads often employ atypical imagery, using surprising object juxtapositions to convey shared properties. For example, Fig. 1 (e) shows a beer with a feather-like texture. This requires advanced reasoning to deduce that this atypical representation signifies the beer's lightness. We introduce three novel tasks, Multi-label Atypicality Classification, Atypicality Statement Retrieval, and Aypical Object Recognition, to benchmark VLMs' understanding of atypicality in persuasive images. We evaluate how well VLMs use atypicality to infer an ad's message and test their reasoning abilities by employing semantically challenging negatives. Finally, we pioneer atypicality-aware verbalization by extracting comprehensive image descriptions sensitive to atypical elements. Our findings reveal that: (1) VLMs lack advanced reasoning capabilities compared to LLMs; (2) simple, effective strategies can extract atypicality-aware information, leading to comprehensive image verbalization; (3) atypicality aids persuasive advertisement understanding. Code and data will be made available.