آمار

تعداد نشریات15
تعداد شماره‌ها239
تعداد مقالات2,431
تعداد مشاهده مقاله4,070,112
تعداد دریافت فایل اصل مقاله2,960,539
KardanMoghaddam, Hossein, Akbarimajd, Adel, Jamali, Shahram, KardanMoghaddam, Hamid. (1405). A New Framework Based on LLM-Based Multi-Agent Systems for Text Classification. فناوری آموزش, (), -. doi: 10.22061/jecei.2026.12349.867
Hossein KardanMoghaddam; Adel Akbarimajd; Shahram Jamali; Hamid KardanMoghaddam. "A New Framework Based on LLM-Based Multi-Agent Systems for Text Classification". فناوری آموزش, , , 1405, -. doi: 10.22061/jecei.2026.12349.867
KardanMoghaddam, Hossein, Akbarimajd, Adel, Jamali, Shahram, KardanMoghaddam, Hamid. (1405). 'A New Framework Based on LLM-Based Multi-Agent Systems for Text Classification', فناوری آموزش, (), pp. -. doi: 10.22061/jecei.2026.12349.867
KardanMoghaddam, Hossein, Akbarimajd, Adel, Jamali, Shahram, KardanMoghaddam, Hamid. A New Framework Based on LLM-Based Multi-Agent Systems for Text Classification. فناوری آموزش, 1405; (): -. doi: 10.22061/jecei.2026.12349.867

A New Framework Based on LLM-Based Multi-Agent Systems for Text Classification

Journal of Electrical and Computer Engineering Innovations (JECEI)
مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 20 تیر 1405
نوع مقاله: Original Research Paper
شناسه دیجیتال (DOI): 10.22061/jecei.2026.12349.867
نویسندگان
Hossein KardanMoghaddam1؛ Adel Akbarimajd* 1؛ Shahram Jamali1؛ Hamid KardanMoghaddam2
1Department of Electrical and Computer Engineering, University of Mohaghegh Ardabili, Ardabili, Iran.
2Water Research Institute, Ministry of Energy Water Research Institute, Tehran, Iran
تاریخ دریافت: 12 اسفند 1404،  تاریخ بازنگری: 06 خرداد 1405،  تاریخ پذیرش: 20 تیر 1405 
چکیده
Background and Objectives: Multi-agent systems that incorporate large language models (LLM-MAS) represent one of the most innovative areas in artificial intelligence. These systems effectively address significant problems across various fields by merging the capabilities of large language models with traditional multi-agent systems (MAS). As science progresses in various domains, the importance of natural language processing, particularly text classification has significantly increased.
Methods: This study introduces an innovative framework for text classification based on a multi-agent voting system. In this framework, four distinct LLMs independently label input text into five predefined categories, assigning a weight to each label. Additionally, five specialized term extraction functions act as independent agents, identifying key concepts related to each label within the text. These functions influence the final decision-making process by adjusting the weights assigned by the language models. The label with the highest aggregated weight is selected as the final classification output.
Results: Experimental results demonstrate that the proposed framework achieves an accuracy of approximately 86%, highlighting the effectiveness of an LLM-based multi-agent approach in text classification tasks.
Conclusion: Fine-tuning large language models typically requires a substantial dataset to effectively personalize the model. This process can be time-consuming and costly, and the resulting model is often limited to a specific application. However, the results of this study demonstrate that the proposed framework can achieve acceptable accuracy without the need for fine-tuning large language models. The study shows that combining term extraction functions with large language models can create smarter and more accurate systems. These term extraction functions modify the weights derived from the large language models, adjusting them toward specific topic labels based on relevant words found in the text.
کلیدواژه‌ها
Large Language Model (LLM)؛ Text Classification؛ Natural Language Processing (NLP)؛ Prompt Engineering؛ Deep Learning
آمار
تعداد مشاهده مقاله: 4


سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب