arXiv 2210.114682022-10-20cs.SEcs.HCcs.LG

ObSynth：一个从自然语言规范生成对象模型的交互式综合系统

ObSynth: An Interactive Synthesis System for Generating Object Models from Natural Language Specifications

Massachusetts Institute of Technology（麻省理工学院）

Alex Gu, Tamara Mitrovska, Daniela Velez, Jacob Andreas, Armando Solar-Lezama

备注：: 25 pages, 15 figures

摘要：

我们介绍ObSynth，一个交互式系统，利用嵌入在大语言模型（LLM）的领域知识，以帮助用户设计对象模型，从高层次的自然语言提示。这是规范具体化的一个例子，将一个高层次的、潜在的模糊规范具体化为一个更具体的形式。我们通过用户研究评估ObSynth，得出三个关键发现：首先，使用ObSynth设计的对象模型更详细，表明它经常合成用户可能忽略的字段。其次，ObSynth生成的大多数对象、方法和字段都由用户保存在最终的对象模型中，突出了生成组件的质量。第三，ObSynth改变了参与者的工作流程：他们专注于检查合成组件是否正确，而不是从头开始生成它们，尽管ObSynth并没有减少参与者生成对象模型的时间。

英文摘要：

We introduce ObSynth, an interactive system leveraging the domain knowledge embedded in large language models (LLMs) to help users design object models from high level natural language prompts. This is an example of specification reification, the process of taking a high-level, potentially vague specification and reifying it into a more concrete form. We evaluate ObSynth via a user study, leading to three key findings: first, object models designed using ObSynth are more detailed, showing that it often synthesizes fields users might have otherwise omitted. Second, a majority of objects, methods, and fields generated by ObSynth are kept by the user in the final object model, highlighting the quality of generated components. Third, ObSynth altered the workflow of participants: they focus on checking that synthesized components were correct rather than generating them from scratch, though ObSynth did not reduce the time participants took to generate object models.

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。

摘要：

英文摘要：

相关论文