# Similar Choices, Different Attention: Cross-Modal Associations in Humans and Vision-Language Models

arXiv: https://arxiv.org/abs/2609.36475 · HTML: https://mlsanity.com/paper/2609.36475/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social bias and fairness in VLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Social bias and fairness in VLMs](https://mlsanity.com/mllm/social-bias-and-fairness-in-vlms/)

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Gemma 4 Technical Report](https://mlsanity.com/paper/2607.02770/) (2026)
- [Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding](https://mlsanity.com/paper/2601.10611/) (2026)
- [Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?](https://mlsanity.com/paper/1606.03556/) (2016)
- [Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs](https://mlsanity.com/paper/2510.17771/) (2025)
- [Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention](https://mlsanity.com/paper/2010.07891/) (2020)
- [Supervising Neural Attention Models for Video Captioning by Human Gaze Data](https://mlsanity.com/paper/1707.06029/) (2017)
- [Kiki or Bouba? Sound Symbolism in Vision-and-Language Models](https://mlsanity.com/paper/2310.16781/) (2023)
- [Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding](https://mlsanity.com/paper/2510.21356/) (2025)
- [With Ears to See and Eyes to Hear: Sound Symbolism Experiments with Multimodal Large Language Models](https://mlsanity.com/paper/2409.14917/) (2024)
- [What does Kiki look like? Cross-modal associations between speech sounds and visual shapes in vision-and-language models](https://mlsanity.com/paper/2407.17974/) (2024)
- [Measuring Sound Symbolism in Audio-visual Models](https://mlsanity.com/paper/2409.12306/) (2024)
- [Do Language Models Associate Sound with Meaning? A Multimodal Study of Sound Symbolism](https://mlsanity.com/paper/2511.10045/) (2025)
- [Cross-modal Associations in Vision and Language Models: Revisiting the Bouba-Kiki Effect](https://mlsanity.com/paper/2507.10013/) (2025)

## Abstract (arXiv)

Cross-modal associations are systematic pairings of features across modalities, such as the association of 'bouba' with round shapes and 'kiki' with sharp shapes. Prior work has compared humans and vision-language models (VLMs) on such associations, but often using different stimuli or tasks between humans and models. Here, we ask whether VLMs align with humans not only in choices, but also in where they look when making those choices. We study both VLMs and humans (N = 53), presenting them with the same stimuli, a pseudo-word and two images, and record participants' choices and eye movements, which we release. We find choice alignment in a few larger VLMs, but their saliency matches human gaze less closely than a center-bias baseline, a fixed Gaussian at the center of each image. Fine-tuning small VLMs on human choices brings their choice alignment to the level of a human majority-vote reference on unseen words and images, yet their attention still matches human gaze less closely than this baseline. Training model attention on human gaze raises attention-gaze correlation without improving choice alignment, and a single average gaze map per image position raises it by a similar amount. Matching human choices, or even human gaze patterns, is therefore not sufficient evidence of human-aligned cross-modal processing.