# Design Theater: Evaluating the Gap Between User-Facing Design Reasoning and Implementation in Generative UI Tools

arXiv: https://arxiv.org/abs/2607.22928 · HTML: https://mlsanity.com/paper/2607.22928/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 65 references that are in the map.
- First posted on arXiv 24 Jul 2026.

## Builds on (most cited first, 25 of 25)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Generative artificial intelligence enhances creativity but reduces the diversity of novel content](https://mlsanity.com/paper/2312.00506/) (2023)
- [Homogenization Effects of Large Language Models on Human Creative Ideation](https://mlsanity.com/paper/2402.01536/) (2024)
- [pix2code: Generating Code from a Graphical User Interface Screenshot](https://mlsanity.com/paper/1705.07962/) (2017)
- [Designing for Responsible Trust in AI Systems: A Communication Perspective](https://mlsanity.com/paper/2204.13828/) (2022)
- [Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study](https://mlsanity.com/paper/2310.02059/) (2023)
- [The Effects of Generative AI on Design Fixation and Divergent Thinking](https://mlsanity.com/paper/2403.11164/) (2024)
- [Screen Parsing: Towards Reverse Engineering of UI Models from Screenshots](https://mlsanity.com/paper/2109.08763/) (2021)
- [Vibe Coding in Practice: Motivations, Challenges, and a Future Outlook -- a Grey Literature Review](https://mlsanity.com/paper/2510.00328/) (2025)
- [Towards interactive evaluations for interaction harms in human-AI systems](https://mlsanity.com/paper/2405.10632/) (2024)
- [Vibe coding: programming through conversation with artificial intelligence](https://mlsanity.com/paper/2506.23253/) (2025)
- [Sketch2Code: Transformation of Sketches to UI in Real-time Using Deep Neural Network](https://mlsanity.com/paper/1910.08930/) (2019)
- [GUIComp: A GUI Design Assistant with Real-Time, Multi-Faceted Feedback](https://mlsanity.com/paper/2001.05684/) (2020)
- [Never-ending Learning of User Interfaces](https://mlsanity.com/paper/2308.08726/) (2023)
- [The GenUI Study: Exploring the Design of Generative UI Tools to Support UX Practitioners and Beyond](https://mlsanity.com/paper/2501.13145/) (2025)
- [Trustworthy Social Bias Measurement](https://mlsanity.com/paper/2212.11672/) (2022)
- [DesignWeaver: Dimensional Scaffolding for Text-to-Image Product Design](https://mlsanity.com/paper/2502.09867/) (2025)
- [Vibe Coding in Product Teams: Reconfiguring AI-Assisted Workflows, Prototyping, and Collaboration](https://mlsanity.com/paper/2509.10652/) (2025)
- [ClearFairy: Capturing Creative Workflows through Decision Structuring, In-Situ Questioning, and Rationale Inference](https://mlsanity.com/paper/2509.14537/) (2025)
- [Co-Designing Collaborative Generative AI Tools for Freelancers](https://mlsanity.com/paper/2602.05299/) (2026)
- [Seeing the Reasoning: How LLM Rationales Influence User Trust and Decision-Making in Factual Verification Tasks](https://mlsanity.com/paper/2603.07306/) (2026)

## Abstract (arXiv)

Generative UI tools promise to democratize UI design by turning natural language descriptions into complete interfaces. Alongside the interface, these tools generate user-facing design rationales that explain their layout, accessibility, and design choices. However, it remains unclear whether these stated rationales are actually reflected in the interfaces they produce. We call this disconnect ``Design Theater'': plausible and confident design rationales that have little relationship to the actual implementation. To study this phenomenon, we introduce a benchmark and three metrics for measuring Design Theater. The benchmark includes 24 UI generation tasks spanning structural, styling, and functional design requirements. Using this benchmark, we evaluate 120 interfaces created by five generative UI tools. On average, over 25% of user-facing design rationales are not implemented in the generated interface, and the implementation failure increases to 34% for functional requirements. Tools recognize roughly half of the UX principles embedded in prompts (mean = 0.54), with four of five tools implementing 6% or fewer functional principles. We also measure interface similarity across tools and find convergence in visual appearance and layout organization, with greater variation in color choices. Overall, we contribute: 1) the concept of Design Theater; 2) a benchmark with metrics for assessing whether the stated reasoning of generative UI tools is reflected in their implementations; 3) and findings from a systematic evaluation of these tools. We discuss what these findings mean for the design and evaluation of generative UI tools.