mlsanityData to 14 Oct 2026

XGen-Q: An Explainable Domain-Adaptive LLM Framework with Retrieval-Augmented Generation for Software Security

arXiv 2510.19006 ↗First posted 21 Oct 2025cs.IRcited by 0

On the map: Retrieval-augmented generation → Privacy and security of RAG

Abstract (arXiv)

Generative AI and large language models (LLMs) have shown strong capabilities in code understanding, but their use in cybersecurity, particularly for malware detection and analysis, remains limited. Existing detection systems often fail to generalize to obfuscated or previously unseen threats, underscoring the need for more adaptable and explainable models. To address this challenge, we introduce XGen-Q, a domain-adapted LLM built on the Qwen-Coder architecture and pretrained on a large-scale corpus of over one million malware samples, spanning both source and assembly code. XGen-Q uses a multi-stage prompt strategy combined with retrieval-augmented generation (RAG) to deliver reliable malware identification and detailed forensic reporting, even in the presence of complex code obfuscation. To further enhance generalization, we design a training pipeline that systematically exposes the model to diverse obfuscation patterns. Experimental results show that XGen-Q achieves significantly lower perplexity than competitive baselines and exhibits strong performance on novel malware samples, demonstrating the promise of LLM-based approaches for interpretable and robust malware analysis.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 18 of its 39 references that are in the map. First posted on arXiv 21 Oct 2025.

Builds on

18 of 39 references.

References · 18

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2017Mixed Precision Trainingcited by 1,156
  5. 2023Large Language Modelscited by 780
  6. 2025Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAscited by 521
  7. 2018Mixed Precision Training of Convolutional Neural Networks using Integer Operationscited by 45
  8. 2024SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domainscited by 28
  9. 2024Causality for Large Language Modelscited by 25
  10. 2025LAMD: Context-driven Android Malware Detection and Classification with LLMscited by 18
  11. 2023Adapt in Contexts: Retrieval-Augmented Domain Adaptation via In-Context Learningcited by 16
  12. 2025Large Language Models (LLMs) for Source Code Analysis: applications, models and datasetscited by 16
6 more
  1. 2025Large Language Model (LLM) for Software Security: Code Analysis, Malware Analysis, Reverse Engineeringcited by 15
  2. 2024Exploring LLMs for Malware Detection: Review, Framework Design, and Countermeasure Approachescited by 13
  3. 2024Perplexed: Understanding When Large Language Models are Confusedcited by 9
  4. 2024Software Security Analysis in 2030 and Beyond: A Research Roadmapcited by 5
  5. 2025Exploring the Role of Large Language Models in Cybersecurity: A Systematic Surveycited by 5
  6. 2025Real-Time Multi-Modal Subcomponent-Level Measurements for Trustworthy System Monitoring and Malware Detectioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025"Digital Camouflage": The LLVM Challenge in LLM-Based Malware Detection
  2. 2026Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies
  3. 2026AsmRAG: LLM-Driven Malware Detection by Retrieving Functionally Similar Assembly Code
  4. 2024Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities
  5. 2026Evaluating Retrieval-Augmented Generation for Explainable Malware Analysis
  6. 2025LLMpatronous: Harnessing the Power of LLMs For Vulnerability Detection
  7. 2025Automated Vulnerability Validation and Verification: A Large Language Model Approach
  8. 2026LCC-LLM: Leveraging Code-Centric Large Language Models for Malware Attribution