# Through the PRISM: Principle-Aware, Interpretable, and Multi-Scale Evaluation of Visual Designs

arXiv: https://arxiv.org/abs/2606.00592 · HTML: https://mlsanity.com/paper/2606.00592/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 55 references that are in the map.
- First posted on arXiv 30 May 2026.

## Builds on (most cited first, 30 of 35)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Ferret: Refer and Ground Anything Anywhere at Any Granularity](https://mlsanity.com/paper/2310.07704/) (2023)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World](https://mlsanity.com/paper/2308.01907/) (2023)
- [BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs](https://mlsanity.com/paper/2307.08581/) (2023)
- [A Thorough Examination of Decoding Methods in the Era of LLMs](https://mlsanity.com/paper/2402.06925/) (2024)
- [CanvasVAE: Learning to Generate Vector Graphic Documents](https://mlsanity.com/paper/2108.01249/) (2021)
- [Attribute-conditioned Layout GAN for Automatic Graphic Design](https://mlsanity.com/paper/2009.05284/) (2020)
- [PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout](https://mlsanity.com/paper/2303.15937/) (2023)
- [Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model](https://mlsanity.com/paper/2312.12423/) (2023)
- [PG-Video-LLaVA: Pixel Grounding Large Video-Language Models](https://mlsanity.com/paper/2311.13435/) (2023)
- [CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Design](https://mlsanity.com/paper/2505.19114/) (2025)
- [Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation](https://mlsanity.com/paper/2311.13602/) (2023)
- [Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time](https://mlsanity.com/paper/2407.01851/) (2024)
- [UICrit: Enhancing Automated Design Evaluation with a UICritique Dataset](https://mlsanity.com/paper/2407.08850/) (2024)
- [VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction](https://mlsanity.com/paper/2412.04237/) (2024)
- [Can GPTs Evaluate Graphic Design Based on Design Principles?](https://mlsanity.com/paper/2410.08885/) (2024)
- [MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks](https://mlsanity.com/paper/2506.07016/) (2025)
- [Demystifying Tacit Knowledge in Graphic Design: Characteristics, Instances, Approaches, and Guidelines](https://mlsanity.com/paper/2403.06252/) (2024)
- [LTSim: Layout Transportation-based Similarity Measure for Evaluating Layout Generation](https://mlsanity.com/paper/2407.12356/) (2024)
- [A Survey for Graphic Design Intelligence](https://mlsanity.com/paper/2309.01371/) (2023)

## Abstract (arXiv)

Effective visual communication stems from the harmony of multiple design principles, such as readability, contrast, alignment, overlap, and coherence, which collectively govern clarity and intent of the communicator. While human designers reason holistically over these principles, machine agents typically condense them into a single heuristic score, offering limited interpretability and diagnostic precision. To address this gap, we introduce PRISM (PRinciple-aware, Interpretable, and Structure-guided Design Modifications), a benchmark that systematically perturbs professional layouts from the Crello dataset along measurable design principles. The benchmark comprises 100K perturbed training samples and 10K perturbed validation designs, each isolating a specific principle violation for controlled analysis of multimodal reasoning about design quality. We show that models like Qwen-2.5-VL and GPT-4o-mini are largely insensitive to targeted principle degradations, whereas GPT-4o exhibits global awareness without fine-grained disentanglement. Building on these insights, we propose a multi-scale evaluation framework that integrates lightweight scorers for quantitative assessment, instruction-tuned vision-language models for localised feedback, and prompt-based methods for global reasoning. Our framework provides interpretable explanations of design failures. Using these localised insights, we show targeted refinements that improve layout quality. Together, PRISM and our framework lay the foundation for interpretable design-literate multimodal reasoning systems.