# WhyGen: Explaining ML-powered Code Generation by Referring to Training Examples

arXiv: https://arxiv.org/abs/2204.07940 · HTML: https://mlsanity.com/paper/2204.07940/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2022.

## Built on by (most cited first, 7 of 7)

- [A Performance Study of LLM-Generated Code on Leetcode](https://mlsanity.com/paper/2407.21579/) (2024)
- [CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation](https://mlsanity.com/paper/2311.08588/) (2023)
- [Copyright Protection in Generative AI: A Technical Perspective](https://mlsanity.com/paper/2402.02333/) (2024)
- [CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification](https://mlsanity.com/paper/2405.00253/) (2024)
- [Scratch Copilot Evaluation: Assessing AI-Assisted Creative Coding for Families](https://mlsanity.com/paper/2305.10417/) (2023)
- [Neural Machine Translation for Code Generation](https://mlsanity.com/paper/2305.13504/) (2023)
- [What Makes Code Generation Ethically Sourced?](https://mlsanity.com/paper/2507.19743/) (2025)

## Abstract (arXiv)

Deep learning has demonstrated great abilities in various code generation tasks. However, despite the great convenience for some developers, many are concerned that the code generators may recite or closely mimic copyrighted training data without user awareness, leading to legal and ethical concerns. To ease this problem, we introduce a tool, named WhyGen, to explain the generated code by referring to training examples. Specifically, we first introduce a data structure, named inference fingerprint, to represent the decision process of the model when generating a prediction. The fingerprints of all training examples are collected offline and saved to a database. When the model is used at runtime for code generation, the most relevant training examples can be retrieved by querying the fingerprint database. Our experiments have shown that WhyGen is able to precisely notify the users about possible recitations and highly similar imitations with a top-10 accuracy of 81.21%. The demo video can be found at https://youtu.be/EtoQP6850To.