1000+电商组件中半数含诱导设计，提示词影响极大
Deception at Scale: Deceptive Designs in 1K LLM-Generated Ecommerce Components
- 用4个大模型生成1296个电商组件，分析其诱导性设计
- 55.8%组件含至少一种诱导设计，30.6%含两种以上
- 强调商业利益的提示词会显著增加诱导设计，价值观导向最有效
近期研究显示，由大型语言模型（LLMs）生成的前端代码可能包含诱导性设计。为评估该问题的严重程度、识别影响诱导设计生成的因素，并测试缓解策略，我们开展了两项研究，生成并分析了1,296个由LLM生成的网页组件，每个组件附有设计说明。第一项研究测试了四种LLM在15种常见电商组件中的表现。结果显示，55.8%的组件包含至少一种诱导设计，30.6%包含两个或更多。不同模型间差异显著，DeepSeek-V3产生的最少。界面干扰成为主要策略，通过色彩心理学影响用户行为，并隐藏关键信息。第一项研究发现，强调商业利益（如提升销量）的提示词显著增加了诱导设计，因此第二项研究测试了多种提示策略以降低其频率，结果表明基于价值观的方法最为有效。研究揭示了使用LLM进行编码的风险，并为开发者和提供商提供了改进建议。
原文摘要 · Abstract (English)
Recent work has shown that front-end code generated by Large Language Models (LLMs) can embed deceptive designs. To assess the magnitude of this problem, identify the factors that influence deceptive design production, and test strategies for reducing deceptive designs, we carried out two studies which generated and analyzed 1,296 LLM-generated web components, along with a design rationale for each. The first study tested four LLMs for 15 common ecommerce components. Overall 55.8% of components contained at least one deceptive design, and 30.6% contained two or more. Occurence varied significantly across models, with DeepSeek-V3 producing the fewest. Interface interference emerged as the dominant strategy, using color psychology to influence actions and hiding essential information. The first study found that prompts emphasizing business interests (e.g., increasing sales) significantly increased deceptive designs, so a second study tested a variety of prompting strategies to reduce their frequency, finding a values-centered approach the most effective. Our findings highlight risks in using LLMs for coding and offer recommendations for LLM developers and providers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。