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

Computer Science > Cryptography and Security [Submitted on 24 Jun 2026] Representation Matters: An Empirical Study of Program Representations for LLM Vulnerability Reasoning Andrew Stoltman, Johnathan Tang, Haipeng Cai 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. RepBench converts real-world C/C++ vulnerability testcases into multiple representations: raw source, Abstract Syntax Trees (ASTs), Control-Flow Graphs (CFGs), Program Dependence Graphs (PDGs), their combinations, and an auxiliary track of enriched PDGs (ePDGs). Using a curated PrimeVul-derived corpus of 107 Joern-based testcases across five CWE categories, we evaluate ten representation variants under a fixed Chain-of-Thought and structured-output protocol, plus 19 additional ePDG cases generated through VulChecker/Hector. Representation choice substantially affects LLM vulnerability reasoning. The strongest variant, AST+PDG, achieves 83.2% accuracy, compared with 53.5% for raw source. At the family level, graph-only prompts outperform both source-only and source-plus-graph prompts while requiring far less prompt overhead. These results reveal a context dilution effect: adding raw source code to compact structural graph evidence can degrade reasoning by making vulnerability-relevant evidence less salient. Overall, our findings show that carefully selected structural representations offer a better accuracy-overhead tradeoff than simply giving LLMs more raw input, and suggest that static analysis can serve as an effective prompt-construction layer for security-focused LLM reasoning. Comments: 34 pages, 4 figures Subjects: Cryptography and Security (cs.CR); Software Engineering (cs.SE) Cite as: arXiv:2606.25356 [cs.CR]   (or arXiv:2606.25356v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.25356 Focus to learn more Submission history From: Andrew Stoltman [view email] [v1] Wed, 24 Jun 2026 03:43:42 UTC (86 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.SE References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)