Enhancing Network Engineering Capabilities through LLM Fine-Tuning with Automatically Generated Datasets.

Saved in:

Bibliographic Details
Title:	Enhancing Network Engineering Capabilities through LLM Fine-Tuning with Automatically Generated Datasets.
Authors:	Trăistaru, Claudiu¹ claudiu.traistaru@edu.ucv.ro, Pop, Florin² florin.pop@upb.ro, Bădică, Costin³ costin.badica@edu.ucv.ro, Mancaş, Cătălina² catalina.mancas@edu.ucv.ro, Murareţu, Ionuţ³ ionut.muraretu@edu.ucv.ro
Source:	Computer Science & Information Systems. Jan2026, Vol. 23 Issue 1, p535-560. 26p.
Subjects:	Routing systems, Computer network security, Telecommunication, Algorithms, Language models
Abstract:	The paper presents a method for automatically generating domain-specific datasets to fine-tune open-source LLMs in network engineering. Our objective is to address the increasingly complex nature of network configuration and management jobs by supplying LLMs with high-quality training data. We evaluated datasets generated using open-source LLMs, including DeepSeek-R1 671B, LLaMA 3.1 70B, Qwen 2.5 72B, and Mixtral 8x7B, analyzing the quality of unprocessed knowledge data and the efficacy of cleaning and deduplication methods. The resulting dataset addresses various subjects related to routing, security, and network services. Afterward, we fine-tuned smaller LLaMA 3.2 1B, LLaMA 3.2 3B and Qwen 2.5 1.5B models using Low-Rank Adaptation, thereby minimizing computational demands while maintaining the quality of domain knowledge. [ABSTRACT FROM AUTHOR]
	Copyright of Computer Science & Information Systems is the property of ComSIS Consortium and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	The paper presents a method for automatically generating domain-specific datasets to fine-tune open-source LLMs in network engineering. Our objective is to address the increasingly complex nature of network configuration and management jobs by supplying LLMs with high-quality training data. We evaluated datasets generated using open-source LLMs, including DeepSeek-R1 671B, LLaMA 3.1 70B, Qwen 2.5 72B, and Mixtral 8x7B, analyzing the quality of unprocessed knowledge data and the efficacy of cleaning and deduplication methods. The resulting dataset addresses various subjects related to routing, security, and network services. Afterward, we fine-tuned smaller LLaMA 3.2 1B, LLaMA 3.2 3B and Qwen 2.5 1.5B models using Low-Rank Adaptation, thereby minimizing computational demands while maintaining the quality of domain knowledge. [ABSTRACT FROM AUTHOR]
ISSN:	18200214
DOI:	10.2298/CSIS250416082T