CORTEXA
← Browse
arxivcs.CVcs.HC2026-07-17

Attention-Guided Saliency Maps for Interpreting Visualization Literacy in VLMs

Maeve Hutchinson, Abderrahmane Wassim Mehdaoui, Pranava Madhyastha

Understanding how vision-language models (VLMs) interpret data visualizations remains an open problem, and is increasingly important as these models are used for analytical tasks where reliable reasoning is essential. We introduce a lightweight, diagnostic saliency map method tailored for text generation over images using transformer models, the current state-of-the-art models in visualization interpretation. Our approach aggregates the language model's attention over the visual tokens across all heads and layers, then maps this attention back onto the vision encoder's patch grid to localise it over the image, producing a direct correspondence between each generated answer token and the image regions it attended to. This yields fast, gradient-free saliency maps that expose how VLMs allocate focus across visual elements during answer generation, enabling inspection of whether model attention aligns with semantically relevant components. We evaluate our approach using a deletion metric which validates the causal faithfulness of our saliency maps to the model's behavior.

View free PDFSource page

Related papers

arxivcs.CVcs.HC2026-07-23

Sidewalk Moments: Are Richer Representations Always More Human-Aligned? Evidence from City-Walk Videos

Liu Liu, Freya Huying Tan, Fábio Duarte

We examine whether richer visual representations yield more human-aligned measures of urban engagement, using 61 first-person city-walk videos from YouTube segmented into over 50,000 ten-second clips and represented across four modalities: spatiotemporal video features, temporall…

View free PDFSource page
arxivcs.CLcs.AIcs.CVcs.HC2026-07-31

FriendBench: Benchmarking Dyadic Familiarity Inference in Humans and Multimodal Large Language Models

Jeffrey M. Girard, Jason Z. Zheng, Jacqueline R. Vertino, Antony D'Avirro, Benjamin Peloquin

Reading a social situation often depends on behavior, not words alone. We introduce FriendBench, a benchmark for inferring whether two people are already familiar or are meeting as strangers, from a 20-second clip of a dyadic ice-breaker conversation. Every pair answers the same…

View free PDFSource page
arxivcs.HC2026-07-31

Data Visualization Style Guides in Practice: Why They Emerge, How They Work, and When They Bend

Alvitta Ottley, Jonathan Schwabish

Visualization style guides play a crucial role in shaping how data is interpreted and trusted, yet they often receive little scrutiny in their creation and use. Understanding their impact requires looking beyond the specific rules that style guides prescribe and examining how the…

View free PDFSource page
arxivcs.MMcs.CV2026-07-24

CARA: Concept-Aware Risk Attention for Interpretable Collision Anticipation

Zhishan Tao, Ruoyu Wang, Yucheng Wu, Enjun Du, Yilei Yuan, Sherwin Ho, et al.

Collision anticipation in autonomous driving requires not only accurate early warnings but also interpretable reasoning about what risk factors are being tracked and how risk evolves over time. Existing methods fall short in this regard: feature-driven models are opaque, post-hoc…

View free PDFSource page