Representation Matters: An Empirical Study of Program Representations for LLM Vulnerability Reasoning

Abstract

Large Language Models (LLMs) are increasingly used for automated vulnerability detection, but it remains unclear how program structure and semantics should be represented for LLM-based reasoning. Most prompting-based approaches provide raw source code, implicitly assuming that more source-level context gives the model better evidence. This paper challenges that assumption through RepBench, an empirical benchmark comparing raw source code with static-analysis-based program representations. RepBen

Categories

@misc{stoltman2026representation,
  title = {{Representation Matters: An Empirical Study of Program Representations for LLM Vulnerability Reasoning}},
  author = {Andrew Stoltman and Johnathan Tang and Haipeng Cai},
  year = {2026},
  month = jun,
  eprint = {2606.25356},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.25356}
}