Leveraging Local LLMs for Secure In-System Task Automation With Prompt-Based Agent Classification
Recent progress in the field of intelligence has led to the creation of powerful large language models (LLMs). While these models show promise in improving personal computing experiences concerns surrounding data privacy and security have hindered their integration with sensitive personal informatio...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10766449/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846141981732896768 |
|---|---|
| author | Suthir Sriram C. H. Karthikeya K. P. Kishore Kumar Nivethitha Vijayaraj Thangavel Murugan |
| author_facet | Suthir Sriram C. H. Karthikeya K. P. Kishore Kumar Nivethitha Vijayaraj Thangavel Murugan |
| author_sort | Suthir Sriram |
| collection | DOAJ |
| description | Recent progress in the field of intelligence has led to the creation of powerful large language models (LLMs). While these models show promise in improving personal computing experiences concerns surrounding data privacy and security have hindered their integration with sensitive personal information. In this study, a new framework is proposed to merge LLMs with personal file systems, enabling intelligent data interaction while maintaining strict privacy safeguards. The methodology organizes tasks based on LLM agents, which apply designated tags to the tasks before sending them to specific LLM modules. Every module is has its own function, including file search, document summarization, code interpretation, and general tasks, to make certain that all processing happens locally on the user’s device. Findings indicate high accuracy across agents: classification agent managed to get an accuracy rating of 86%, document summarization reached a BERT score of 0.9243. The key point of this framework is that it splits the LLM system into modules, which enables future development by integrating new task-specific modules as required. Findings suggest that integrating local LLMs can significantly improve interactions with file systems without compromising data privacy. |
| format | Article |
| id | doaj-art-7dabf0f3d18c455ab0913ad131ba31d0 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-7dabf0f3d18c455ab0913ad131ba31d02024-12-04T00:00:46ZengIEEEIEEE Access2169-35362024-01-011217703817704910.1109/ACCESS.2024.350529810766449Leveraging Local LLMs for Secure In-System Task Automation With Prompt-Based Agent ClassificationSuthir Sriram0https://orcid.org/0000-0003-2480-3273C. H. Karthikeya1https://orcid.org/0009-0006-4774-5562K. P. Kishore Kumar2https://orcid.org/0009-0000-6607-0771Nivethitha Vijayaraj3https://orcid.org/0000-0002-8694-033XThangavel Murugan4https://orcid.org/0000-0002-2510-8857Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Chennai, IndiaDepartment of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Chennai, IndiaDepartment of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Chennai, IndiaDepartment of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Chennai, IndiaCollege of Information and Technology, United Arab Emirates University, Al Ain, United Arab EmiratesRecent progress in the field of intelligence has led to the creation of powerful large language models (LLMs). While these models show promise in improving personal computing experiences concerns surrounding data privacy and security have hindered their integration with sensitive personal information. In this study, a new framework is proposed to merge LLMs with personal file systems, enabling intelligent data interaction while maintaining strict privacy safeguards. The methodology organizes tasks based on LLM agents, which apply designated tags to the tasks before sending them to specific LLM modules. Every module is has its own function, including file search, document summarization, code interpretation, and general tasks, to make certain that all processing happens locally on the user’s device. Findings indicate high accuracy across agents: classification agent managed to get an accuracy rating of 86%, document summarization reached a BERT score of 0.9243. The key point of this framework is that it splits the LLM system into modules, which enables future development by integrating new task-specific modules as required. Findings suggest that integrating local LLMs can significantly improve interactions with file systems without compromising data privacy.https://ieeexplore.ieee.org/document/10766449/File systemfew-shot promptingLangChainLLMprompt engineering |
| spellingShingle | Suthir Sriram C. H. Karthikeya K. P. Kishore Kumar Nivethitha Vijayaraj Thangavel Murugan Leveraging Local LLMs for Secure In-System Task Automation With Prompt-Based Agent Classification IEEE Access File system few-shot prompting LangChain LLM prompt engineering |
| title | Leveraging Local LLMs for Secure In-System Task Automation With Prompt-Based Agent Classification |
| title_full | Leveraging Local LLMs for Secure In-System Task Automation With Prompt-Based Agent Classification |
| title_fullStr | Leveraging Local LLMs for Secure In-System Task Automation With Prompt-Based Agent Classification |
| title_full_unstemmed | Leveraging Local LLMs for Secure In-System Task Automation With Prompt-Based Agent Classification |
| title_short | Leveraging Local LLMs for Secure In-System Task Automation With Prompt-Based Agent Classification |
| title_sort | leveraging local llms for secure in system task automation with prompt based agent classification |
| topic | File system few-shot prompting LangChain LLM prompt engineering |
| url | https://ieeexplore.ieee.org/document/10766449/ |
| work_keys_str_mv | AT suthirsriram leveraginglocalllmsforsecureinsystemtaskautomationwithpromptbasedagentclassification AT chkarthikeya leveraginglocalllmsforsecureinsystemtaskautomationwithpromptbasedagentclassification AT kpkishorekumar leveraginglocalllmsforsecureinsystemtaskautomationwithpromptbasedagentclassification AT nivethithavijayaraj leveraginglocalllmsforsecureinsystemtaskautomationwithpromptbasedagentclassification AT thangavelmurugan leveraginglocalllmsforsecureinsystemtaskautomationwithpromptbasedagentclassification |