View in EDS PDF Full Text

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
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 192054657
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Enhancing Network Engineering Capabilities through LLM Fine-Tuning with Automatically Generated Datasets.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Trăistaru%2C+Claudiu%22">Trăistaru, Claudiu</searchLink><relatesTo>1</relatesTo><i> claudiu.traistaru@edu.ucv.ro</i><br /><searchLink fieldCode="AR" term="%22Pop%2C+Florin%22">Pop, Florin</searchLink><relatesTo>2</relatesTo><i> florin.pop@upb.ro</i><br /><searchLink fieldCode="AR" term="%22Bădică%2C+Costin%22">Bădică, Costin</searchLink><relatesTo>3</relatesTo><i> costin.badica@edu.ucv.ro</i><br /><searchLink fieldCode="AR" term="%22Mancaş%2C+Cătălina%22">Mancaş, Cătălina</searchLink><relatesTo>2</relatesTo><i> catalina.mancas@edu.ucv.ro</i><br /><searchLink fieldCode="AR" term="%22Murareţu%2C+Ionuţ%22">Murareţu, Ionuţ</searchLink><relatesTo>3</relatesTo><i> ionut.muraretu@edu.ucv.ro</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Computer+Science+%26+Information+Systems%22">Computer Science & Information Systems</searchLink>. Jan2026, Vol. 23 Issue 1, p535-560. 26p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Routing+systems%22">Routing systems</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+network+security%22">Computer network security</searchLink><br /><searchLink fieldCode="DE" term="%22Telecommunication%22">Telecommunication</searchLink><br /><searchLink fieldCode="DE" term="%22Algorithms%22">Algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Language+models%22">Language models</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: 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]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>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.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=192054657
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.2298/CSIS250416082T
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 26
        StartPage: 535
    Subjects:
      – SubjectFull: Routing systems
        Type: general
      – SubjectFull: Computer network security
        Type: general
      – SubjectFull: Telecommunication
        Type: general
      – SubjectFull: Algorithms
        Type: general
      – SubjectFull: Language models
        Type: general
    Titles:
      – TitleFull: Enhancing Network Engineering Capabilities through LLM Fine-Tuning with Automatically Generated Datasets.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Trăistaru, Claudiu
      – PersonEntity:
          Name:
            NameFull: Pop, Florin
      – PersonEntity:
          Name:
            NameFull: Bădică, Costin
      – PersonEntity:
          Name:
            NameFull: Mancaş, Cătălina
      – PersonEntity:
          Name:
            NameFull: Murareţu, Ionuţ
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Text: Jan2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 18200214
          Numbering:
            – Type: volume
              Value: 23
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Computer Science & Information Systems
              Type: main
ResultId 1