arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.17348cs.SEcs.HC
收藏

科学家如何使用大型语言模型进行编程

How Scientists Use Large Language Models to Program

Gabrielle O'Brien

AI总结:

该研究通过访谈公立研究型大学的科学家并分析交互日志,发现早期采用代码生成大模型的科学家多将其用作信息检索工具学习陌生编程工具,同时揭示了相关验证策略及代码生成可能影响科研分析参数的潜在风险。

摘要:

各学科的科学家会为数据收集与生成、统计建模、可视化等关键工作编写代码。随着可生成代码的大型语言模型(Large Language Model, LLM)广泛普及,科学家在科研软件开发过程中可能会越来越多地使用这类模型。我们对一所公立研究型大学的科学家开展访谈,调研代码生成模型早期采用者的特征。通过访谈与用户交互日志分析,我们发现科学家常将代码生成模型当作信息检索工具,用于学习不熟悉的编程语言和库。我们还呈现了关于他们验证策略的研究结果,并讨论了代码生成实践在无意中影响科学分析参数可能带来的潜在风险。

英文摘要:

Scientists across disciplines write code for critical activities like data collection and generation, statistical modeling, and visualization. As large language models that can generate code have become widely available, scientists may increasingly use these models during research software development. We investigate the characteristics of scientists who are early-adopters of code generating models and conduct interviews with scientists at a public, research-focused university. Through interviews and reviews of user interaction logs, we see that scientists often use code generating models as an information retrieval tool for navigating unfamiliar programming languages and libraries. We present findings about their verification strategies and discuss potential vulnerabilities that may emerge from code generation practices unknowingly influencing the parameters of scientific analyses.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑