LLaVul: A Multimodal LLM for Interpretable Vulnerability Reasoning about Source Code
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911168171343872 |
|---|---|
| author | Jararweh, Ala Adams, Michael Sahu, Avinash Mueen, Abdullah Anwar, Afsah |
| author_facet | Jararweh, Ala Adams, Michael Sahu, Avinash Mueen, Abdullah Anwar, Afsah |
| contents | Increasing complexity in software systems places a growing demand on reasoning tools that unlock vulnerabilities manifest in source code. Many current approaches focus on vulnerability analysis as a classifying task, oversimplifying the nuanced and context-dependent real-world scenarios. Even though current code large language models (LLMs) excel in code understanding, they often pay little attention to security-specific reasoning. We propose LLaVul, a multimodal LLM tailored to provide fine-grained reasoning about code through question-answering (QA). Our model is trained to integrate paired code and natural queries into a unified space, enhancing reasoning and context-dependent insights about code vulnerability. To evaluate our model performance, we construct a curated dataset of real-world vulnerabilities paired with security-focused questions and answers. Our model outperforms state-of-the-art general-purpose and code LLMs in the QA and detection tasks. We further explain decision-making by conducting qualitative analysis to highlight capabilities and limitations. By integrating code and QA, LLaVul enables more interpretable and security-focused code understanding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17337 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLaVul: A Multimodal LLM for Interpretable Vulnerability Reasoning about Source Code Jararweh, Ala Adams, Michael Sahu, Avinash Mueen, Abdullah Anwar, Afsah Artificial Intelligence Computation and Language Increasing complexity in software systems places a growing demand on reasoning tools that unlock vulnerabilities manifest in source code. Many current approaches focus on vulnerability analysis as a classifying task, oversimplifying the nuanced and context-dependent real-world scenarios. Even though current code large language models (LLMs) excel in code understanding, they often pay little attention to security-specific reasoning. We propose LLaVul, a multimodal LLM tailored to provide fine-grained reasoning about code through question-answering (QA). Our model is trained to integrate paired code and natural queries into a unified space, enhancing reasoning and context-dependent insights about code vulnerability. To evaluate our model performance, we construct a curated dataset of real-world vulnerabilities paired with security-focused questions and answers. Our model outperforms state-of-the-art general-purpose and code LLMs in the QA and detection tasks. We further explain decision-making by conducting qualitative analysis to highlight capabilities and limitations. By integrating code and QA, LLaVul enables more interpretable and security-focused code understanding. |
| title | LLaVul: A Multimodal LLM for Interpretable Vulnerability Reasoning about Source Code |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2509.17337 |