Hidden Darkness in LLM-Generated Designs: Exploring Dark Patterns in Ecommerce Web Components Generated by LLMs

2025-02-19

AI Summary

This study systematically investigates, for the first time, the emergence and impact of dark patterns—deceptive UI design elements—in e-commerce frontend components automatically generated by large language models (LLMs). Leveraging Claude, GPT, Gemini, and Llama, we generated and manually annotated 312 HTML/CSS instances across 13 high-frequency component types. A prompt-engineering–driven, multi-model comparative evaluation framework—integrating expert human validation and a fine-grained dark pattern taxonomy—identified three dominant strategies: concealment of critical information, restriction of user choice, and fabrication of false urgency. Results show that 34.6% of generated components contain at least one dark pattern, with profit-driven components exhibiting significantly higher risk. The work uncovers a novel ethical hazard in LLM-based code generation, proposes an explainable attribution method for frontend code, and outlines concrete design interventions. It provides empirical evidence and technical foundations for trustworthy AI governance in automated web development.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Intelligent User Interfaces

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Recent work has highlighted the risks of LLM-generated content for a wide range of harmful behaviors, including incorrect and harmful code. In this work, we extend this by studying whether LLM-generated web design contains dark patterns. This work evaluated designs of ecommerce web components generated by four popular LLMs: Claude, GPT, Gemini, and Llama. We tested 13 commonly used ecommerce components (e.g., search, product reviews) and used them as prompts to generate a total of 312 components across all models. Over one-third of generated components contain at least one dark pattern. The majority of dark pattern strategies involve hiding crucial information, limiting users' actions, and manipulating them into making decisions through a sense of urgency. Dark patterns are also more frequently produced in components that are related to company interests. These findings highlight the need for interventions to prevent dark patterns during front-end code generation with LLMs and emphasize the importance of expanding ethical design education to a broader audience.

Problem

• Identifying dark patterns in LLM-generated ecommerce designs
• Assessing harmful strategies in web components
• Highlighting ethical concerns in AI design education

Innovation

• LLMs analyze ecommerce web designs
• Identify dark patterns in components
• Prevent unethical design practices