# Knowledge-Enhanced Program Repair for Data Science Code

arXiv: https://arxiv.org/abs/2502.09771 · HTML: https://mlsanity.com/paper/2502.09771/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2025.

## Built on by (most cited first, 6 of 6)

- [Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches](https://mlsanity.com/paper/2510.04905/) (2025)
- [SGAgent: Suggestion-Guided LLM-Based Multi-Agent Framework for Repository-Level Software Repair](https://mlsanity.com/paper/2602.23647/) (2026)
- [Rethinking Autonomy: Preventing Failures in AI-Driven Software Engineering](https://mlsanity.com/paper/2508.11824/) (2025)
- [ViTAD: Timing Violation-Aware Debugging of RTL Code using Large Language Models](https://mlsanity.com/paper/2508.13257/) (2025)
- [Collaborative Agents for Automated Program Repair in Ruby](https://mlsanity.com/paper/2511.03925/) (2025)
- [Beyond Execution: Static-Analysis Rewards and Hint-Conditioned Diffusion RL for Code Generation](https://mlsanity.com/paper/2605.17174/) (2026)

## Abstract (arXiv)

This paper introduces DSrepair, a knowledge-enhanced program repair method designed to repair the buggy code generated by LLMs in the data science domain. DSrepair uses knowledge graph based RAG for API knowledge retrieval as well as bug knowledge enrichment to construct repair prompts for LLMs. Specifically, to enable knowledge graph based API retrieval, we construct DS-KG (Data Science Knowledge Graph) for widely used data science libraries. For bug knowledge enrichment, we employ an abstract syntax tree (AST) to localize errors at the AST node level. DSrepair's effectiveness is evaluated against five state-of-the-art LLM-based repair baselines using four advanced LLMs on the DS-1000 dataset. The results show that DSrepair surpasses all five baselines. Specifically, when compared to the second-best baseline, DSrepair demonstrates significant improvements, fixing 44.4%, 14.2%, 20.6%, and 32.1% more buggy code snippets for each of the four evaluated LLMs, respectively. Additionally, it achieves greater efficiency, reducing the number of tokens required per code task by 17.49%, 34.24%, 24.71%, and 17.59%, respectively.