# Fine-tuning of Large Language Models for Domain-Specific Cybersecurity Knowledge

arXiv: https://arxiv.org/abs/2509.25241 · HTML: https://mlsanity.com/paper/2509.25241/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 31 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems](https://mlsanity.com/paper/1508.01745/) (2015)
- [Let the LLMs Talk: Simulating Human-to-Human Conversational QA via Zero-Shot LLM-to-LLM Interactions](https://mlsanity.com/paper/2312.02913/) (2023)
- [Compression Represents Intelligence Linearly](https://mlsanity.com/paper/2404.09937/) (2024)
- [CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge](https://mlsanity.com/paper/2402.07688/) (2024)
- [Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications](https://mlsanity.com/paper/2403.16073/) (2024)
- [Iterative Zero-Shot LLM Prompting for Knowledge Graph Construction](https://mlsanity.com/paper/2307.01128/) (2023)
- [Deep Learning for Optimization of Trajectories for Quadrotors](https://mlsanity.com/paper/2309.15191/) (2023)
- [Dynamic Rank Adjustment in Diffusion Policies for Efficient and Flexible Training](https://mlsanity.com/paper/2502.03822/) (2025)
- [Legal Documents Drafting with Fine-Tuned Pre-Trained Large Language Model](https://mlsanity.com/paper/2406.04202/) (2024)

## Built on by (most cited first, 1 of 1)

- [Security Document Classification with a Fine-Tuned Local Large Language Model: Benchmark Data and an Open-Source System](https://mlsanity.com/paper/2605.20368/) (2026)

## Abstract (arXiv)

Recent advancements in training paradigms for Large Language Models (LLMs) have unlocked their remarkable capabilities in natural language processing and cross-domain generalization. While LLMs excel in tasks like programming and mathematical problem-solving, their zero-shot performance in specialized domains requiring expert knowledge, such as cybersecurity, is often suboptimal. This limitation arises because foundational LLMs are designed for general-purpose applications, constraining their ability to encapsulate domain-specific expertise within their parameter space. To address this, we explore fine-tuning strategies to embed cybersecurity knowledge into LLMs, enhancing their performance in cybersecurity question-answering (Q&A) tasks while prioritizing computational efficiency. Specifically, we investigate Supervised Fine-Tuning (SFT), Low-Rank Adaptation (LoRA), and Quantized Low-Rank Adaptation (QLoRA) using a cybersecurity Q&A dataset. Our results demonstrate that these fine-tuning approaches significantly outperform the foundational model in cybersecurity Q&A tasks. Moreover, LoRA and QLoRA achieve comparable performance to SFT with substantially lower computational costs, offering an efficient pathway for adapting LLMs to specialized domains. Our work highlights the potential of low-rank fine-tuning strategies to bridge the gap between general-purpose LLMs and domain-specific applications.