SketchFill: Sketch-Guided Code Generation for Imputing Derived Missing Values

Yunfan Zhang, Changlun Li, Yuyu Luo, Nan Tang

Keywords: Large Language Model;Missing Value Impuation;Data Preprocessing;Code Generation

TL;DR: We propose a sketch-guided and self-reflected code generation approach to impute missing values for tabular data.

Abstract: Missing value is a critical issue in data science, significantly impacting the reliability of analyses and predictions. Missing value imputation (MVI) is a longstanding problem because it highly relies on domain knowledge. Large language models (LLMs) have emerged as a promising tool for data cleaning, including MVI for tabular data, offering advanced capabilities for understanding and generating content. However, despite their promise, existing LLM techniques such as in-context learning and Chain-of-Thought (CoT) often fall short in guiding LLMs to perform complex reasoning for MVI, particularly when imputing derived missing values, which require mathematical formulas and data relationships across rows and columns. This gap underscores the need for further advancements in LLM methodologies to enhance their reasoning capabilities for more reliable imputation outcomes. To fill this gap, we propose SketchFill, a novel sketch-based method to guide LLMs in generating accurate formulas to impute missing numerical values. SketchFill first utilizes a general user-provided Meta-Sketch to generate a Domain-Sketch tailored to the context of the input dirty table. Subsequently, it fills this Domain-Sketch with formulas and outputs Python code, effectively bridging the gap between high-level abstractions and executable solutions. Additionally, SketchFill incorporates a Reflector component to verify the generated code. This Reflector assesses the accuracy and appropriateness of the outputs and iteratively refines the Domain-Sketch, ensuring that the imputation aligns closely with the underlying data patterns and relationships. Our experimental results demonstrate that SketchFill significantly outperforms state-of-the-art methods, achieving 56.2% higher accuracy than CoT-based methods and 78.8% higher accuracy than MetaGPT. This sets a new standard for automated data cleaning and advances the field of MVI for numerical values.

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 9233