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

arXiv: https://arxiv.org/abs/2412.19113 · HTML: https://mlsanity.com/paper/2412.19113/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 43 references that are in the map.
- First posted on arXiv 26 Dec 2024.

## Builds on (most cited first, 17 of 17)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Using an LLM to Help With Code Understanding](https://mlsanity.com/paper/2307.08177/) (2023)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study](https://mlsanity.com/paper/2305.13062/) (2023)
- [CERT: Continual Pre-Training on Sketches for Library-Oriented Code Generation](https://mlsanity.com/paper/2206.06888/) (2022)
- [Diffusion models for missing value imputation in tabular data](https://mlsanity.com/paper/2210.17128/) (2022)
- [Table-GPT: Table-tuned GPT for Diverse Table Tasks](https://mlsanity.com/paper/2310.09263/) (2023)
- [RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases](https://mlsanity.com/paper/2004.03125/) (2020)
- [Extractive Summarization via ChatGPT for Faithful Summary Generation](https://mlsanity.com/paper/2304.04193/) (2023)
- [AI-assisted coding: Experiments with GPT-4](https://mlsanity.com/paper/2304.13187/) (2023)
- [SkCoder: A Sketch-based Approach for Automatic Code Generation](https://mlsanity.com/paper/2302.06144/) (2023)
- [Large Language Models as Data Preprocessors](https://mlsanity.com/paper/2308.16361/) (2023)
- [Less is More for Long Document Summary Evaluation by LLMs](https://mlsanity.com/paper/2309.07382/) (2023)
- [What You Need is What You Get: Theory of Mind for an LLM-Based Code Understanding Assistant](https://mlsanity.com/paper/2408.04477/) (2024)
- [Missing Value Imputation for Multi-attribute Sensor Data Streams via Message Propagation (Extended Version)](https://mlsanity.com/paper/2311.07344/) (2023)

## Built on by (most cited first, 2 of 2)

- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)

## Abstract (arXiv)

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. 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.