Efficient multilingual spam detection on resource-constrained devices: a comparative analysis of QLoRA fine-tuning of Gemma 3, Qwen 3, and Llama 3.2 models.
Uloženo v:
| Název: | Efficient multilingual spam detection on resource-constrained devices: a comparative analysis of QLoRA fine-tuning of Gemma 3, Qwen 3, and Llama 3.2 models. |
|---|---|
| Autoři: | Rauf, Hamza, Khan, Umair, Bashatah, Jomana A., Zaib, Aurang |
| Zdroj: | Complex & Intelligent Systems; Mar2026, Vol. 12 Issue 3, p1-26, 26p |
| Abstrakt: | Modern spam is worldwide and multilingual, making advanced detection difficult for resource-constrained devices to balance with user privacy and efficiency. The lack of multilingual training data and the high computing cost of Large Language Models hinder traditional solutions. A secure, privacy-preserving framework for multilingual spam classifier development is presented and tested in this research. First, we synthetically generate a balanced, 21-language dataset by high-fidelity translating the English Enron corpus using the Aya-101 model to handle data scarcity. Next, we use Quantized Low-Rank Adaptation to effectively fine-tune the 4-bit quantized versions of leading compact LLMs Gemma 3-4B, Qwen 3-4B, and Llama 3.2-3B in a thorough comparison. QLoRA-tuned models improve significantly, with the Gemma 3-4B model performing best with 90% accuracy and 0.88 F1-score. A stunning 22-percentage-point increase above its 16-bit baseline. The fine-tuned models also reduced VRAM footprint significantly, proving their on-device feasibility. QLoRA and synthetic data pipelines provide a compelling, practical blueprint for implementing cutting-edge AI in privacy-sensitive, resource-constrained situations, according to this research. [ABSTRACT FROM AUTHOR] |
| Copyright of Complex & Intelligent Systems is the property of Springer Nature 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.) | |
| Databáze: | Complementary Index |
Full Text Finder 
Nájsť tento článok vo Web of Science | FullText | Text: Availability: 0 CustomLinks: – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edb&genre=article&issn=21994536&ISBN=&volume=12&issue=3&date=20260301&spage=1&pages=1-26&title=Complex & Intelligent Systems&atitle=Efficient%20multilingual%20spam%20detection%20on%20resource-constrained%20devices%3A%20a%20comparative%20analysis%20of%20QLoRA%20fine-tuning%20of%20Gemma%203%2C%20Qwen%203%2C%20and%20Llama%203.2%20models.&aulast=Rauf%2C%20Hamza&id=DOI:10.1007/s40747-026-02247-x Name: Full Text Finder Category: fullText Text: Full Text Finder Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif MouseOverText: Full Text Finder – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Rauf%20H Name: ISI Category: fullText Text: Nájsť tento článok vo Web of Science Icon: https://imagesrvr.epnet.com/ls/20docs.gif MouseOverText: Nájsť tento článok vo Web of Science |
|---|---|
| Header | DbId: edb DbLabel: Complementary Index An: 192061663 RelevancyScore: 1082 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 1082.41040039063 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Efficient multilingual spam detection on resource-constrained devices: a comparative analysis of QLoRA fine-tuning of Gemma 3, Qwen 3, and Llama 3.2 models. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Rauf%2C+Hamza%22">Rauf, Hamza</searchLink><br /><searchLink fieldCode="AR" term="%22Khan%2C+Umair%22">Khan, Umair</searchLink><br /><searchLink fieldCode="AR" term="%22Bashatah%2C+Jomana+A%2E%22">Bashatah, Jomana A.</searchLink><br /><searchLink fieldCode="AR" term="%22Zaib%2C+Aurang%22">Zaib, Aurang</searchLink> – Name: TitleSource Label: Source Group: Src Data: Complex & Intelligent Systems; Mar2026, Vol. 12 Issue 3, p1-26, 26p – Name: Abstract Label: Abstract Group: Ab Data: Modern spam is worldwide and multilingual, making advanced detection difficult for resource-constrained devices to balance with user privacy and efficiency. The lack of multilingual training data and the high computing cost of Large Language Models hinder traditional solutions. A secure, privacy-preserving framework for multilingual spam classifier development is presented and tested in this research. First, we synthetically generate a balanced, 21-language dataset by high-fidelity translating the English Enron corpus using the Aya-101 model to handle data scarcity. Next, we use Quantized Low-Rank Adaptation to effectively fine-tune the 4-bit quantized versions of leading compact LLMs Gemma 3-4B, Qwen 3-4B, and Llama 3.2-3B in a thorough comparison. QLoRA-tuned models improve significantly, with the Gemma 3-4B model performing best with 90% accuracy and 0.88 F1-score. A stunning 22-percentage-point increase above its 16-bit baseline. The fine-tuned models also reduced VRAM footprint significantly, proving their on-device feasibility. QLoRA and synthetic data pipelines provide a compelling, practical blueprint for implementing cutting-edge AI in privacy-sensitive, resource-constrained situations, according to this research. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Group: Ab Data: <i>Copyright of Complex & Intelligent Systems is the property of Springer Nature 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://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=192061663 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s40747-026-02247-x Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 26 StartPage: 1 Titles: – TitleFull: Efficient multilingual spam detection on resource-constrained devices: a comparative analysis of QLoRA fine-tuning of Gemma 3, Qwen 3, and Llama 3.2 models. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Rauf, Hamza – PersonEntity: Name: NameFull: Khan, Umair – PersonEntity: Name: NameFull: Bashatah, Jomana A. – PersonEntity: Name: NameFull: Zaib, Aurang IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 03 Text: Mar2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 21994536 Numbering: – Type: volume Value: 12 – Type: issue Value: 3 Titles: – TitleFull: Complex & Intelligent Systems Type: main |
| ResultId | 1 |