Problem
Research questions and friction points this paper is trying to address.
personalization
bias
generative AI
software engineering
developer identity
Biased or Personalized? The Impact of Personal Information on AI-driven Development
🤖 AI Summary
This study investigates how developers’ personal attributes—such as age and gender—unintentionally introduce bias into AI-generated code, thereby compromising its objectivity and fairness. Through the generation of 800 websites using large language models, controlled experiments, user interviews, and qualitative analysis, the research systematically examines identity-induced disparities in AI outputs across three dimensions: interface design, template content, and code structure. The work presents the first empirical evidence of significant identity-related biases in AI-assisted programming. Based on findings from 20 participants, it further reveals divergent perceptions among developers regarding the boundary between personalization and fairness, highlighting a novel tension between these competing values. These insights offer both theoretical grounding and practical guidance for designing more equitable AI programming tools.
📝 Abstract
Generative AI is increasingly permeating software engineering, enabling developers to generate functions, files, and even entire applications from natural language specifications. AI systems are also becoming more personalized, adapting outputs based on inferred user characteristics and interaction history. While personalization may improve the development experience, it raises concerns that generated software could be shaped by attributes of the developer rather than by task requirements alone. Prior work has shown that generative AI can produce biased software artifacts, but little is known about how developer identity can bias generated code. We characterize three dimensions through which inferred developer attributes can influence generated artifacts: interface design, template content, and code structure. First, through controlled experiments on 800 AI-generated websites, we find that age- and gender-related signals produce significant differences across all three dimensions. Second, we conduct an observational study and follow-up interviews with 20 participants who used AI to create a personal website to both examine how personalization impacts software artifacts in practice, and also to understand how programmers perceive the boundary between personalization and bias. Together, our results show that developer attributes can meaningfully influence generated software beyond stated requirements, highlighting a previously underexplored tension between personalization and fairness in AI-assisted programming.
Innovation
Methods, ideas, or system contributions that make the work stand out.
personalization
bias
generative AI
software engineering
developer identity
🔎 Similar Papers
No similar papers found.
