← Back to all news
arXiv Computer Vision By Nurb\"uke Teker, Rui Xiao, Zeynep Akata, Shuchen Wu

Feature Competition and Its Representational Origins in Vision Language Models: Evidence from the Stroop Paradigm

Read the original on arXiv Computer Vision →

The paper investigates how vision‑language models (VLMs) resolve conflicts between image features using a Stroop‑style benchmark. By prompting contrastive and generative VLMs on images where text and color disagree, the authors find a consistent bias toward textual cues, with models preferring to respond based on text rather than color. Analysis of the embedding space reveals that textual signals are represented more strongly and separably than color signals, explaining why steering models toward text is easier than toward color.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Aug 24

What Color Is the Text? A Benchmark for Hallucination Induced by Image-Embedded Prompt

The paper introduces Embedded Stroop, a diagnostic test that embeds text prompts directly into images to study interference in multimodal large language models (MLLMs). Using the What-Color-Is-the-Text (WCIT) benchmark, which tests 59 fine‑grained colors in standard, flipped, and masked conditions, the authors evaluate 16 models and find that while exact color accuracy is low (6.3%), models still recognize coarse color families (38.4%) but frequently hallucinate the embedded word instead of the true color (Stroop Hallucination Rate of 21.6%). Masking or flipping the embedded text reduces hallucinations, indicating that semantic legibility can dominate visual color perception in MLLMs.

By Jinkun Zhao, Lei Huang, Haixin Ge, Wenjun Wu
llmsmultimodalbenchmarkssafety
More like this →
arXiv Computation and Language
Sep 11

Do Vision-Language Models Understand Visual Persuasiveness? A Diagnosis via Visual Persuasive Factors

The paper investigates whether Vision‑Language Models (VLMs) can understand visual persuasiveness by evaluating image‑message pairs that humans consistently judge as persuasive. It introduces Visual Persuasive Factors (VPFs), a taxonomy from cognitive psychology, to quantify visual cues influencing persuasive judgments. Empirical analysis shows VLMs tend to over‑predict persuasiveness, partially reproducing human patterns but often generating false positives, and that VPF‑guided interventions can improve performance only when properly framed.

By Gyuwon Park, Hyounghun Kim
llmsmultimodalsafety
More like this →