用交互式结构化编程工具，让人类与AI协作快速构建可解释的科学数据分析系统。
Engineering Systems for Data Analysis Using Interactive Structured Inductive Programming
- 通过双向可解释协议，将任务分解为数据流图并逐步生成代码。
- 在天体物理和生物化学项目中，开发速度提升百倍，代码质量更高。
- 适合需要快速构建可信分析系统的研究团队使用。
面向科学数据分析的信息系统工程面临诸多挑战：复杂工作流需探索巨大解空间，需与领域专家紧密协作，且要求系统可维护、可解释。传统手工开发耗时，而基于大语言模型的“无代码”方法常产生不可靠系统。本文提出iProg，一种实现交互式结构化归纳编程的工具。iProg采用一种‘双向可解释性’通信协议，约束人与LLM协作构建系统。给定自然语言描述的数据分析任务，iProg首先利用LLM将问题分解为声明式表示（数据流图DFD）；第二阶段再由LLM为每个DFD节点生成代码。两阶段均通过协议提供的结构化反馈验证输出。我们在两个已发表的科研合作项目（天体物理与生物化学）上全面评估iProg，证明其能有效识别合适系统分解，并构建端到端信息系统，相比低代码/无代码方案，性能更优、代码质量更高、开发速度提升一个数量级。工具地址：https://shraddhasurana.github.io/dhaani/
原文摘要 · Abstract (English)
Engineering information systems for scientific data analysis presents significant challenges: complex workflows requiring exploration of large solution spaces, close collaboration with domain specialists, and the need for maintainable, interpretable implementations. Traditional manual development is time-consuming, while "No Code" approaches using large language models (LLMs) often produce unreliable systems. We present iProg, a tool implementing Interactive Structured Inductive Programming. iProg employs a variant of a '2-way Intelligibility' communication protocol to constrain collaborative system construction by a human and an LLM. Specifically, given a natural-language description of the overall data analysis task, iProg uses an LLM to first identify an appropriate decomposition of the problem into a declarative representation, expressed as a Data Flow Diagram (DFD). In a second phase, iProg then uses an LLM to generate code for each DFD process. In both stages, human feedback, mediated through the constructs provided by the communication protocol, is used to verify LLMs' outputs. We evaluate iProg extensively on two published scientific collaborations (astrophysics and biochemistry), demonstrating that it is possible to identify appropriate system decompositions and construct end-to-end information systems with better performance, higher code quality, and order-of-magnitude faster development compared to Low Code/No Code alternatives. The tool is available at: https://shraddhasurana.github.io/dhaani/
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。