# Generating Unseen Code Tests In Infinitum

arXiv: https://arxiv.org/abs/2407.19772 · HTML: https://mlsanity.com/paper/2407.19772/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 12 references that are in the map.
- First posted on arXiv 29 Jul 2024.

## Builds on (most cited first, 5 of 5)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code](https://mlsanity.com/paper/2302.05527/) (2023)
- [Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code](https://mlsanity.com/paper/2311.07989/) (2023)
- [NAPS: Natural Program Synthesis Dataset](https://mlsanity.com/paper/1807.03168/) (2018)

## Abstract (arXiv)

Large Language Models (LLMs) are used for many tasks, including those related to coding. An important aspect of being able to utilize LLMs is the ability to assess their fitness for specific usages. The common practice is to evaluate LLMs against a set of benchmarks. While benchmarks provide a sound foundation for evaluation and comparison of alternatives, they suffer from the well-known weakness of leaking into the training data citeXu2024Benchmarking. We present a method for creating benchmark variations that generalize across coding tasks and programming languages, and may also be applied to in-house code bases. Our approach enables ongoing generation of test-data thus mitigating the leaking into the training data issue. We implement one benchmark, called textitauto-regression, for the task of text-to-code generation in Python. Auto-regression is specifically created to aid in debugging and in tracking model generation changes as part of the LLM regression testing process.