# Engineering Systems for Data Analysis Using Interactive Structured Inductive Programming

arXiv: https://arxiv.org/abs/2503.14488 · HTML: https://mlsanity.com/paper/2503.14488/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 47 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Builds on (most cited first, 13 of 13)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [Structured Prompting: Scaling In-Context Learning to 1,000 Examples](https://mlsanity.com/paper/2212.06713/) (2022)
- [LLMs for Science: Usage for Code Generation and Data Analysis](https://mlsanity.com/paper/2311.16733/) (2023)
- [UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback](https://mlsanity.com/paper/2406.07739/) (2024)
- [Machine Learning and Big Scientific Data](https://mlsanity.com/paper/1910.07631/) (2019)
- [Guiding Enumerative Program Synthesis with Large Language Models](https://mlsanity.com/paper/2403.03997/) (2024)
- [Unlocking Structured Thinking in Language Models with Cognitive Prompting](https://mlsanity.com/paper/2410.02953/) (2024)
- [Towards a Grounded Dialog Model for Explainable Artificial Intelligence](https://mlsanity.com/paper/1806.08055/) (2018)
- [Program Synthesis using Inductive Logic Programming for the Abstraction and Reasoning Corpus](https://mlsanity.com/paper/2405.06399/) (2024)
- [Predicting star formation properties of galaxies using deep learning](https://mlsanity.com/paper/2002.03578/) (2020)

## Built on by (most cited first, 3 of 3)

- [Structured Program Synthesis using LLMs: Results and Insights from the IPARC Challenge](https://mlsanity.com/paper/2506.13820/) (2025)
- [Don't Let Me Ask for It: LLMs Show Deficiencies in Active Multi-Turn Information Acquisition for Abductive Inference](https://mlsanity.com/paper/2608.03388/) (2026)
- [Identifying Latent Declarative Representations of Code for Assisting Repository Migration](https://mlsanity.com/paper/2608.23619/) (2026)

## Abstract (arXiv)

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/