Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.14500 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911322902364160 |
|---|---|
| author | Poncu, Teodor Pintilie, Ioana Dragoi, Marius Tantaru, Dragos Brad, Florin |
| author_facet | Poncu, Teodor Pintilie, Ioana Dragoi, Marius Tantaru, Dragos Brad, Florin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_14500 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | C-ing Clearly: Enhanced Binary Code Explanations using C code Poncu, Teodor Pintilie, Ioana Dragoi, Marius Tantaru, Dragos Brad, Florin Computation and Language Machine Learning 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. |
| title | C-ing Clearly: Enhanced Binary Code Explanations using C code |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2512.14500 |