کنفرانس مهندسی برق ایران

صفحه اصلی / سی و دومین کنفرانس بین المللی مهندسی برق

TELLM: Advancements in Knowledge Incorporation and Task-specific Enhancements of Large Language Models

نویسندگان :

Fatemeh Feizi¹ Amirhossein Hossein Nia² MohammadMahdi Hemmatyar³ Fatemeh Rahimi⁴ Farhoud Jafari Kaleibar⁵

1- ایرانسل 2- ایرانسل 3- ایرانسل 4- ایرانسل 5- ایرانسل

کلمات کلیدی :

Large Language Model،Deep Learning،Telecom،Question-answering

چکیده :

Customer service is crucial for any business to maintain good customer relationships and growth. However, addressing a wide variety of customer inquiries often requires deep domain expertise that may not be readily available. This paper presents TELLM, a customer service AI agent leveraging large language models to provide technical support for telecom companies. TELLM is trained using a knowledge base containing categorized technical solutions through dual-phase fine-tuning. It is further refined through reinforcement learning with feedback from subject matter experts. Evaluation on a real-world customer service dataset demonstrates TELLM outperforms prior approaches on automatic metrics and achieves high scores in human evaluation for response accuracy, clarity and effectiveness.

لیست مقالات

لیست مقالات بایگانی شده

بازشناسی مقاوم زمانی – مکانی انسان در یک سیستم نظارتی بر اساس شبکه GAN

آزاده سادات موسوی - شهریار برادران شکوهی

Contextual Based Locality Preserving Projection for Classification of SAR Images with Multiple Polarizations

Maryam Imani

A Dual-Band LPDA Antenna Based on MXene for High-Band 5G Application

Javad Shokri seyyedi - Reza Sarraf Shirazi - Gholamreza Moradi

Higher-order semi-blind source separation approaches using Canonical Polyadic (CP) decomposition

Mohammad Jalilpour Monesi - Sepideh Hajipour Sardouie

Integration of Deep Learning Techniques in Stock Market Forecasting: xLSTM-CNN with RevIN and Adaptive Wavelet Denoising

Alireza Mohammadi - Ali Doustmohammadi - Masoud Shafiee

Contextual and Spectral Feature Fusion Using Local Binary Graph for Hyperspectral Images Classification

Zahra Farmahini Farahani - Hassan Ghassemian - Maryam Imani

Average Secrecy Capacity Performance Analysis for SWIPT-Based SIMO Underlay Cognitive Radio

Mohammad Javad Saber1 - Seyedeh Maryam Mazloum - Seyed Mohammad Sajad Sadough

بهبود تاب‌آوری شبکه‌های توزیع سنتی در مرحله پیش از حادثه به کمک بازآرایی با الگوریتم ارگانیسم همزیستی

حسین بایسته - رضا شیردره - محمد احمدوند

Introduce a novel approach to orbital maintenance in CRTBP

Amirreza Kosari - Ehsan Abbasali - Jamileh Hamzei - Majid Bakhtiari

U-Net-based Automotive Radar Target Detection and Recognition

Jamal Kazazi - Seyyed Mohammad Matin AleMohammad - Mahmoud Kamarei

بیشتر

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 41.7.4