Evaluating perturbation robustnessof generative systems that use COBOL code inputs

• URL: http://arxiv.org/abs/2511.18488v1
• Date: Sun, 23 Nov 2025 15:16:08 GMT
• Title: Evaluating perturbation robustnessof generative systems that use COBOL code inputs
• Abstract summary: Systems incorporating large language models (LLMs) as a component are known to be sensitive (i.e., non-robust) to minor input variations.<n>Here, we present a framework to evaluate robustness of systems using code as input.
• Score: 1.3327839779221817
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• SEDCoT: Enhancing LLM-Based COBOL Code Translation via Symbolic Execution and Delta Debugging [49.898541267264115]
  Maintenance is increasingly challenging due to outdated technologies, sparse documentation, and developer retirement.<n>Traditional rule-based transcompilers yield outputs that are difficult to read and maintain.<n>We propose SEDCoT, a novel-to-C translation framework.
  arXiv  Detail & Related papers  (2026-07-05T03:07:10Z)
• Not All Tokens Matter: Data-Centric Optimization for Efficient Code Summarization [46.365359894614706]
  We evaluate how system prompts affect ILMs and CLMs in code generation tasks.<n>Our evaluation framework, spanning 120 model configurations, reveals that the influence of system prompts increases with model scale.<n>Java shows greater sensitivity to system prompt variations than Python.
  arXiv  Detail & Related papers  (2026-01-28T00:45:28Z)
• Code Review Without Borders: Evaluating Synthetic vs. Real Data for Review Recommendation [37.86790434630698]
  Large Language Models (LLMs) are used to translate code changes from well-resourced languages into equivalent changes in underrepresented or emerging languages.<n>We compare the performance of these models against models trained on real labelled data.<n>This approach provides a scalable pathway to extend automated code review capabilities to rapidly evolving technology stacks.
  arXiv  Detail & Related papers  (2025-09-05T05:17:14Z)
• Quality Evaluation of COBOL to Java Code Transformation [0.22499166814992438]
  We present an automated evaluation system for assessing code translation within IBM's watsonx Code Assistant for Z (WCA4Z)<n>The system addresses key challenges in evaluating LLM-based translators, including model opacity and the complexity of translation quality assessment.
  arXiv  Detail & Related papers  (2025-07-31T09:06:20Z)
• Is Compression Really Linear with Code Intelligence? [60.123628177110206]
  textitFormat Annealing is a lightweight, transparent training methodology designed to assess the intrinsic capabilities of pre-trained models equitably.<n>Our empirical results reveal a fundamental logarithmic relationship between measured code intelligence and bits-per-character (BPC)<n>Our work provides a more nuanced understanding of compression's role in developing code intelligence and contributes a robust evaluation framework in the code domain.
  arXiv  Detail & Related papers  (2025-05-16T16:59:14Z)
• Type-Constrained Code Generation with Language Models [51.03439021895432]
  We introduce a type-constrained decoding approach that leverages type systems to guide code generation.<n>For this purpose, we develop novel prefix automata and a search over inhabitable types, forming a sound approach to enforce well-typedness on LLM-generated code.<n>Our approach reduces compilation errors by more than half and significantly increases functional correctness in code synthesis, translation, and repair tasks.
  arXiv  Detail & Related papers  (2025-04-12T15:03:00Z)
• Enhancing Input-Label Mapping in In-Context Learning with Contrastive Decoding [71.01099784480597]
  Large language models (LLMs) excel at a range of tasks through in-context learning (ICL)<n>We introduce In-Context Contrastive Decoding (ICCD), a novel method that emphasizes input-label mapping.
  arXiv  Detail & Related papers  (2025-02-19T14:04:46Z)
• Guess & Sketch: Language Model Guided Transpilation [59.02147255276078]
  Learned transpilation offers an alternative to manual re-writing and engineering efforts. Probabilistic neural language models (LMs) produce plausible outputs for every input, but do so at the cost of guaranteed correctness. Guess & Sketch extracts alignment and confidence information from features of the LM then passes it to a symbolic solver to resolve semantic equivalence.
  arXiv  Detail & Related papers  (2023-09-25T15:42:18Z)
• On Symbolically Encoding the Behavior of Random Forests [21.79165388471151]
  Recent work has shown that the input-output behavior of some machine learning systems can be captured symbolically. We address systems with discrete inputs and outputs, including ones with discretized continuous variables. We show some key distinctions with encodings for satisfiability, and propose an encoding that is sound and complete for the given task.
  arXiv  Detail & Related papers  (2020-07-03T04:21:47Z)
• Synthetic Datasets for Neural Program Synthesis [66.20924952964117]
  We propose a new methodology for controlling and evaluating the bias of synthetic data distributions over both programs and specifications. We demonstrate, using the Karel DSL and a small Calculator DSL, that training deep networks on these distributions leads to improved cross-distribution generalization performance.
  arXiv  Detail & Related papers  (2019-12-27T21:28:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.