# ReCode: Robustness Evaluation of Code Generation Models

arXiv: https://arxiv.org/abs/2212.10264 · HTML: https://mlsanity.com/paper/2212.10264/

## Key facts

- Cited by 103 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 20 Dec 2022.

## Builds on (most cited first, 26 of 26)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [InCoder: A Generative Model for Code Infilling and Synthesis](https://mlsanity.com/paper/2204.05999/) (2022)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [Dynabench: Rethinking Benchmarking in NLP](https://mlsanity.com/paper/2104.14337/) (2021)
- [Unified Pre-training for Program Understanding and Generation](https://mlsanity.com/paper/2103.06333/) (2021)
- [Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models](https://mlsanity.com/paper/2111.02840/) (2021)
- [Multi-lingual Evaluation of Code Generation Models](https://mlsanity.com/paper/2210.14868/) (2022)
- [Natural Attack for Pre-trained Models of Code](https://mlsanity.com/paper/2201.08698/) (2022)
- [NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation](https://mlsanity.com/paper/2112.02721/) (2021)
- [NatGen: Generative pre-training by "Naturalizing" source code](https://mlsanity.com/paper/2206.07585/) (2022)
- [CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models](https://mlsanity.com/paper/2206.00052/) (2022)
- [Adversarial Robustness for Code](https://mlsanity.com/paper/2002.04694/) (2020)
- [Word-level Textual Adversarial Attacking as Combinatorial Optimization](https://mlsanity.com/paper/1910.12196/) (2019)
- [Adversarial Robustness of Deep Code Comment Generation](https://mlsanity.com/paper/2108.00213/) (2021)
- [Automatic Construction of Evaluation Suites for Natural Language Generation Datasets](https://mlsanity.com/paper/2106.09069/) (2021)
- [Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back Translation](https://mlsanity.com/paper/1910.03009/) (2019)

## Built on by (most cited first, 30 of 103)

- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion](https://mlsanity.com/paper/2310.11248/) (2023)
- [Granite Code Models: A Family of Open Foundation Models for Code Intelligence](https://mlsanity.com/paper/2405.04324/) (2024)
- [Language Models Still Struggle to Zero-shot Reason about Time Series](https://mlsanity.com/paper/2404.11757/) (2024)
- [Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey](https://mlsanity.com/paper/2412.20367/) (2024)
- [EffiBench: Benchmarking the Efficiency of Automatically Generated Code](https://mlsanity.com/paper/2402.02037/) (2024)
- [CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences](https://mlsanity.com/paper/2403.09032/) (2024)
- [Bias Testing and Mitigation in LLM-based Code Generation](https://mlsanity.com/paper/2309.14345/) (2023)
- [A Performance Study of LLM-Generated Code on Leetcode](https://mlsanity.com/paper/2407.21579/) (2024)
- [Model Merging and Safety Alignment: One Bad Model Spoils the Bunch](https://mlsanity.com/paper/2406.14563/) (2024)
- [Measuring The Impact Of Programming Language Distribution](https://mlsanity.com/paper/2302.01973/) (2023)
- [The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers](https://mlsanity.com/paper/2404.02806/) (2024)
- [CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?](https://mlsanity.com/paper/2408.10718/) (2024)
- [MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation](https://mlsanity.com/paper/2405.11430/) (2024)
- [ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation](https://mlsanity.com/paper/2503.07010/) (2025)
- [BioCoder: A Benchmark for Bioinformatics Code Generation with Large Language Models](https://mlsanity.com/paper/2308.16458/) (2023)
- [Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2401.00788/) (2024)
- [IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators](https://mlsanity.com/paper/2403.03894/) (2024)
- [Large Language Model Reasoning Failures](https://mlsanity.com/paper/2602.06176/) (2026)
- [NLPerturbator: Studying the Robustness of Code LLMs to Natural Language Variations](https://mlsanity.com/paper/2406.19783/) (2024)
- [Exploring the Robustness of Large Language Models for Solving Programming Problems](https://mlsanity.com/paper/2306.14583/) (2023)
- [Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates](https://mlsanity.com/paper/2402.05980/) (2024)
- [What can Large Language Models Capture about Code Functional Equivalence?](https://mlsanity.com/paper/2408.11081/) (2024)
- [CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning](https://mlsanity.com/paper/2504.14119/) (2025)
- [On Benchmarking Code LLMs for Android Malware Analysis](https://mlsanity.com/paper/2504.00694/) (2025)
- [T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning](https://mlsanity.com/paper/2506.01317/) (2025)

## Abstract (arXiv)

Code generation models have achieved impressive performance. However, they tend to be brittle as slight edits to a prompt could lead to very different generations; these robustness properties, critical for user experience when deployed in real-life applications, are not well understood. Most existing works on robustness in text or code tasks have focused on classification, while robustness in generation tasks is an uncharted area and to date there is no comprehensive benchmark for robustness in code generation. In this paper, we propose ReCode, a comprehensive robustness evaluation benchmark for code generation models. We customize over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format. They are carefully designed to be natural in real-life coding practice, preserve the original semantic meaning, and thus provide multifaceted assessments of a model's robustness performance. With human annotators, we verified that over 90% of the perturbed prompts do not alter the semantic meaning of the original prompt. In addition, we define robustness metrics for code generation models considering the worst-case behavior under each type of perturbation, taking advantage of the fact that executing the generated code can serve as objective evaluation. We demonstrate ReCode on SOTA models using HumanEval, MBPP, as well as function completion tasks derived from them. Interesting observations include: better robustness for CodeGen over InCoder and GPT-J; models are most sensitive to syntax perturbations; more challenging robustness evaluation on MBPP over HumanEval.