0% Complete
فارسی
Home
/
پانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
Evaluating LLMs in Persian News Summarization
Authors :
Arya VarastehNezhad
1
Reza Tavasoli
2
Mostafa Masumi
3
Seyed Soroush Majd
4
Mehrnoush Shamsfard
5
1- University of Tehran
2- University of South Carolina
3- Sharif University of Technology
4- shahid beheshti university
5- shahid beheshti university
Keywords :
Text Summarization،Large Language Models،Persian News،LLM Evaluation،Natural Language Processing،Artificial Intelligence
Abstract :
This study evaluates the performance of eight Large Language Models (LLMs) in Persian news summarization: GPT-4o, Claude-3.5-Sonnet, Gemini-Pro-1.5, Llama-3.1-405B, Command-R, Mistral-Large-2, DeepSeek V2.5, and Gemma-2-9B. We assess these models across five news categories: Economy, International, Sports, Technology, and Social, using the pn_summary dataset. Our evaluation employs multiple metrics, including BERTScore and ROUGE, across two input conditions: article-only and article-with-title. Results show that Llama-3.1-405b performed best against reference summaries in the article-only setting, achieving the highest BERTScore F1 (50.60) and ROUGE-L (33.96) scores. Notably, including article titles helped models produce summaries which aligned more closely to the reference summary, increasing the average BERTScore F1 from 48.31 to 50.16 across most models. Moreover, when comparing generated summaries to original articles, Mistral-Large-2 led with a BERTScore F1 of 48.09. In category-specific analysis, Mistral-Large-2 consistently outperformed the reference summaries across all news categories, with the most significant improvement in the Economic category. This study provides valuable insights into the current capabilities of LLMs for Persian summarization, highlighting their potential and the impact of input structure on performance. Our findings contribute to the growing body of research on multilingual summarization and have practical implications for Persian language processing applications.
Papers List
List of archived papers
A Hybrid Method to Reduce the Voltage Consumption in the Spiking Neural Networks
Shaghayegh Mehdizadeh saraj - Seyyed Amir Asghari - Mohammadreza Binesh Marvasti
بررسی روش یادگیری انتقالی جهت پیشبینی پیوند
علی روحانی فر - کمال میرزایی بدرآبادی
Web Service Ranking based on QoS and Use Prefer
Seyed Hossein Siadat - Danial Ramezani - Fatemeh Ahani
A Community-Based Method for Identifying Influential Nodes using Network Embedding
Nargess Vafaei - Dr Mohammad Reza Keyvanpour
Movable Antenna Design for UAV-Aided Federated Learning via Deep Reinforcement Learning
MOHSEN Ahmadzadeh - Saeid Pakravan - Ghosheh Abed Hodtani
Fast Duplicate Bug Reports Detector Training using Sampling for Dimension Reduction
Behzad Soleimani Neysiani - Saeed Doostali - Seyed Morteza Babamir - Zahra Aminoroaya
Statistical Disorder Parameters Computing For Hyperspectral Image Anomaly Detection
Dr Maryam Imani
Improving Deep Neural Network Accelerator for Malaria Diseased Blood Cells using FPGA
Hadi Rezaeikarjani - Mojtaba Valinataj
بهبود دقت و کارایی در شبکههای عصبی کانولوشنی با استفاده از روشهای محاسبات تقریبی
محمدرضا رفیعی نژاد - محمدرضا بینش مروستی - سید امیر اصغری
Enhancing kNN-Based Intrusion Detection with Differential Evolution with Auto-Enhanced Population Diversity
Zohre Karimi - Zeinab Torabi
more
Samin Hamayesh - Version 42.5.2