# Evaluating perturbation robustness of generative systems that use COBOL code inputs

arXiv: https://arxiv.org/abs/2511.18488 · HTML: https://mlsanity.com/paper/2511.18488/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 23 Nov 2025.

## Builds on (most cited first, 9 of 9)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [ReCode: Robustness Evaluation of Code Generation Models](https://mlsanity.com/paper/2212.10264/) (2022)
- [Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements](https://mlsanity.com/paper/2401.06766/) (2024)
- [Improving the Robustness of Large Language Models via Consistency Alignment](https://mlsanity.com/paper/2403.14221/) (2024)
- [A Novel Metric for Measuring the Robustness of Large Language Models in Non-adversarial Scenarios](https://mlsanity.com/paper/2408.01963/) (2024)
- [X-COBOL: A Dataset of COBOL Repositories](https://mlsanity.com/paper/2306.04892/) (2023)
- [Enhancing COBOL Code Explanations: A Multi-Agents Approach Using Large Language Models](https://mlsanity.com/paper/2507.02182/) (2025)

## Abstract (arXiv)

Systems incorporating large language models (LLMs) as a component are known to be sensitive (i.e., non-robust) to minor input variations that do not change the meaning of the input; such sensitivity may reduce the system's usefulness. Here, we present a framework to evaluate robustness of systems using COBOL code as input; our application is translation between COBOL and Java programming languages, but the approach extends to other tasks such as code generation or explanation. Targeting robustness of systems with COBOL as input is essential yet challenging. Many business-critical applications are written in COBOL, yet these are typically proprietary legacy applications and their code is unavailable to LLMs for training. We develop a library of COBOL paragraph and full-program perturbation methods, and create variant-expanded versions of a benchmark dataset of examples for a specific task. The robustness of the LLM-based system is evaluated by measuring changes in values of individual and aggregate metrics calculated on the system's outputs. Finally, we present a series of dynamic table and chart visualization dashboards that assist in debugging the system's outputs, and monitoring and understanding root causes of the system's sensitivity to input variation. These tools can be further used to improve the system by, for instance, indicating variations that should be handled by pre-processing steps.