软件工程师对LLM的依赖、过度依赖与成瘾行为研究
原标题：Exploring Dependence, Overreliance, and Addiction Related Behaviors Associated with Large Language Model Use Among Software Engineers
AI 摘要
一项针对119名软件从业者的探索性调查显示，大型语言模型（LLM）已深度融入日常开发工作，主要体现为功能性依赖，并出现过度依赖的迹象，如优先使用LLM而非文档或同行咨询，但成瘾相关行为较少。研究建议通过信任校准、专业判断和验证来促进合理依赖。
正文节选
Computer Science > Software Engineering Title:Exploring Dependence, Overreliance, and Addiction Related Behaviors Associated with Large Language Model Use Among Software Engineers View PDF HTML (experimental) Abstract:The widespread adoption of Large Language Models (LLMs) has changed how software engineers perform everyday development activities. While these systems provide substantial support for tasks such as code generation, debugging, and documentation, their increasing integrat