The paper investigates whether adding textual personas to vision‑language models (VLMs) causes the models to perceive images as the described individuals do. Experiments across 14 VLMs show that persona prompts never outperform simple rule‑based baselines and actually erase real differences between groups such as people with low vision, color blindness, or hearing loss. While the models can predict how visual impairments affect humans, the personas do not alter the models’ image representations or answer probabilities, indicating that the models merely state what they know about people rather than seeing like them.
arXiv:2608.29590v1 Announce Type: new Abstract: We propose a societal bias evaluation method for large vision-language models (LVLMs) in the era of strong safety guardrails. Existing benchmarks rely...
The paper evaluates Vision Language Models (VLMs) on Visual Question Answering tasks where questions violate Grice's maxims. By generating question modifiers that add non-essential, ambiguous, or false information, the authors show that VLMs such as ChatGPT, Claude, Gemini, and Llava exhibit reduced performance. They also compare human pragmatic reasoning to VLM reasoning, noting differences in how each handles human‑induced versus AI‑generated violations, and find that humans spend less time resolving VLM‑induced violations while VLMs are less accurate in those cases.
arXiv:2609.18345v1 Announce Type: new Abstract: Large vision-language models (LVLMs) are commonly used with only a single text prompt as the input, or plus an image. In this paper, we demonstrate tha...
The paper investigates whether vision‑language models (VLMs) can communicate visually in ways similar to humans. It reports that simple visual symbols, such as a red heart, can unexpectedly steer VLMs toward recursive solutions in unrelated tasks, revealing a generation‑interpretation gap where models produce intuitive shapes that do not effectively influence other models. In more complex communication games, VLMs can creatively use visuals to convey abstract concepts, though some messages remain unintuitive to humans, highlighting both the potential and the challenges of visual communication between humans and VLMs.
Vision‑language models (VLMs) can lose accuracy when images are resized, even with minimal changes. The study shows that such small visual configuration changes—like tiling or token arrangement—cause more correctness flips across multiple checkpoints and benchmarks. Interestingly, in many cases the models still read the correct answer but fail to use it, and attention interventions reveal that configuration shifts weaken the use of readable information. By guiding models with field cues and their own transcriptions, the authors correct 97.2% of these errors.
arXiv:2603.04419v3 Announce Type: replace-cross Abstract: Vision-language models produce different object and use descriptions under different persona prompts, but low overlap alone does not identify...
arXiv:2603.03989v4 Announce Type: replace-cross Abstract: An electrical outlet can look like a face without depicting a person. Face pareidolia is thus a revealing probe of how vision models turn amb...
CounterCount is a diagnostic dataset that pairs factual and counterfactual images to test whether Vision‑Language Models (VLMs) rely on visual evidence or on world knowledge when counting attributes. Humans achieve near‑perfect accuracy on both types of images, whereas VLMs drop from 91.6% to 49.5% on counterfactuals, often defaulting to canonical counts. The study shows that VLMs exhibit a System‑1‑like bias, underutilize visual evidence, and that targeted input manipulations can mitigate this bias.
arXiv:2609.05540v1 Announce Type: cross Abstract: Many medical conditions require diagnosis through detailed, multi-context clinical assessment rather than from visual appearance alone. Despite this,...
The paper "Sorry Robot, Happy Human: Vision-Language Models Read Only One of Two Legible Typographic Layers" reports that vision‑language models (VLMs) struggle to read images containing two overlapping text layers—one with sharp contour lines and one with soft shading. Using the DecoyBench dataset of 300 such images, the authors evaluated six closed‑source VLMs under naive and guided prompting at high and low resolutions. While humans could read both layers accurately, the models reliably read only the contour layer at high resolution and failed to extract the shading layer; at low resolution, neither the models nor humans could read the contour layer, but the shading layer remained readable. "whyItMatters":"The study highlights a consistent limitation of current VLMs in handling typographic structures with multiple spatial frequency layers, underscoring their vulnerability to typographic attacks and the need for more robust text‑recognition capabilities."
arXiv:2610.19407v1 Announce Type: new Abstract: Vision-language models must reconcile conflicting text and images. Prior work has characterized the resulting behavior in terms of modality biases--e.g...