English

C-ing Clearly: Enhanced Binary Code Explanations using C code

Computation and Language 2025-12-17 v1 Machine Learning

Abstract

Large Language Models (LLMs) typically excel at coding tasks involving high-level programming languages, as opposed to lower-level programming languages, such as assembly. We propose a synthetic data generation method named C-ing Clearly, which leverages the corresponding C code to enhance an LLM's understanding of assembly. By fine-tuning on data generated through our method, we demonstrate improved LLM performance for binary code summarization and vulnerability detection. Our approach demonstrates consistent gains across different LLM families and model sizes.

Keywords

Cite

@article{arxiv.2512.14500,
  title  = {C-ing Clearly: Enhanced Binary Code Explanations using C code},
  author = {Teodor Poncu and Ioana Pintilie and Marius Dragoi and Dragos Tantaru and Florin Brad},
  journal= {arXiv preprint arXiv:2512.14500},
  year   = {2025}
}

Comments

18 pages, 5 figures