# SkCoder: A Sketch-based Approach for Automatic Code Generation

arXiv: https://arxiv.org/abs/2302.06144 · HTML: https://mlsanity.com/paper/2302.06144/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2023.

## Built on by (most cited first, 30 of 40)

- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Structured Chain-of-Thought Prompting for Code Generation](https://mlsanity.com/paper/2305.06599/) (2023)
- [Self-Edit: Fault-Aware Code Editor for Code Generation](https://mlsanity.com/paper/2305.04087/) (2023)
- [EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories](https://mlsanity.com/paper/2404.00599/) (2024)
- [DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories](https://mlsanity.com/paper/2405.19856/) (2024)
- [Large Language Models for Supply Chain Optimization](https://mlsanity.com/paper/2307.03875/) (2023)
- [Exploring and Unleashing the Power of Large Language Models in Automated Code Translation](https://mlsanity.com/paper/2404.14646/) (2024)
- [Large Language Model-Aware In-Context Learning for Code Generation](https://mlsanity.com/paper/2310.09748/) (2023)
- [Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models](https://mlsanity.com/paper/2309.02772/) (2023)
- [EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations](https://mlsanity.com/paper/2410.22821/) (2024)
- [Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models](https://mlsanity.com/paper/2308.10462/) (2023)
- [CodeS: Natural Language to Code Repository via Multi-Layer Sketch](https://mlsanity.com/paper/2403.16443/) (2024)
- [AceCoder: Utilizing Existing Code to Enhance Code Generation](https://mlsanity.com/paper/2303.17780/) (2023)
- [An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities](https://mlsanity.com/paper/2501.13742/) (2025)
- [Exploring the Potential of Diffusion Large Language Models in Code Generation](https://mlsanity.com/paper/2509.11252/) (2025)
- [Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models](https://mlsanity.com/paper/2407.00456/) (2024)
- [Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?](https://mlsanity.com/paper/2306.01220/) (2023)
- [FRANC: A Lightweight Framework for High-Quality Code Generation](https://mlsanity.com/paper/2307.08220/) (2023)
- [Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code](https://mlsanity.com/paper/2410.09997/) (2024)
- [De-fine: Decomposing and Refining Visual Programs with Auto-Feedback](https://mlsanity.com/paper/2311.12890/) (2023)
- [DevEval: Evaluating Code Generation in Practical Software Projects](https://mlsanity.com/paper/2401.06401/) (2024)
- [Understanding the Fundamental Design Decisions of Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2411.19463/) (2024)
- [Building A Coding Assistant via the Retrieval-Augmented Language Model](https://mlsanity.com/paper/2410.16229/) (2024)
- [Impact-driven Context Filtering For Cross-file Code Completion](https://mlsanity.com/paper/2508.05970/) (2025)
- [Multi-Agent GraphRAG: A Text-to-Cypher Framework for Labeled Property Graphs](https://mlsanity.com/paper/2511.08274/) (2025)
- [A Study on Training and Developing Large Language Models for Behavior Tree Generation](https://mlsanity.com/paper/2401.08089/) (2024)
- [Showing LLM-Generated Code Selectively Based on Confidence of LLMs](https://mlsanity.com/paper/2410.03234/) (2024)
- [Neural Machine Translation for Code Generation](https://mlsanity.com/paper/2305.13504/) (2023)
- [ZC3: Zero-Shot Cross-Language Code Clone Detection](https://mlsanity.com/paper/2308.13754/) (2023)
- [NLP4PBM: A Systematic Review on Process Extraction using Natural Language Processing with Rule-based, Machine and Deep Learning Methods](https://mlsanity.com/paper/2409.13738/) (2024)

## Abstract (arXiv)

Recently, deep learning techniques have shown great success in automatic code generation. Inspired by the code reuse, some researchers propose copy-based approaches that can copy the content from similar code snippets to obtain better performance. Practically, human developers recognize the content in the similar code that is relevant to their needs, which can be viewed as a code sketch. The sketch is further edited to the desired code. However, existing copy-based approaches ignore the code sketches and tend to repeat the similar code without necessary modifications, which leads to generating wrong results. In this paper, we propose a sketch-based code generation approach named SkCoder to mimic developers' code reuse behavior. Given a natural language requirement, SkCoder retrieves a similar code snippet, extracts relevant parts as a code sketch, and edits the sketch into the desired code. Our motivations are that the extracted sketch provides a well-formed pattern for telling models "how to write". The post-editing further adds requirement-specific details to the sketch and outputs the complete code. We conduct experiments on two public datasets and a new dataset collected by this work. We compare our approach to 20 baselines using 5 widely used metrics. Experimental results show that (1) SkCoder can generate more correct programs, and outperforms the state-of-the-art - CodeT5-base by 30.30%, 35.39%, and 29.62% on three datasets. (2) Our approach is effective to multiple code generation models and improves them by up to 120.1% in Pass@1. (3) We investigate three plausible code sketches and discuss the importance of sketches. (4) We manually evaluate the generated code and prove the superiority of our SkCoder in three aspects.