Farig Sadeque

BNLI: A Linguistically-Refined Bengali Dataset for Natural Language Inference

Mohammed Nasheed Yasin, Md. Shoaib Akhter Rafi, Farig Sadeque

Despite the growing progress in Natural Language Inference (NLI) research, resources for the Bengali language remain extremely limited.Existing Bengali NLI datasets exhibit several inconsistencies, including annotation errors, ambiguous sentence pairs, and inadequate linguistic diversity, which hinder effective model training and evaluation.To address …

bd (code pays fourni par la source)

Clinical Note Generation From Doctor-Patient Conversations Using Parameter-Efficient Fine-Tuning Large Language Models: Comparative Study

Saib Ahmed, Farig Sadeque

Background: Clinical note documentation is a vital yet time-intensive task in health care. While advancements in natural language processing have transformed many domains, generating accurate summaries of doctor-patient conversations remains underexplored due to the limited availability of open-source datasets. Large language models …

bd (code pays fourni par la source)

BengaliMCQ: Structure-Aware Retrieval-Augmented Generation for MCQ Generation and Answer Prediction in a Low-Resource Language

Abu Tarabin Surzo, A. K. M. Nihalul Kabir, Sm Azmain Faysal, Ariana Haque Ami et autres

bd (code pays fourni par la source)

A Comparative Analysis of Retrieval-Augmented Generation Techniques for Bengali Standard-to-Dialect Machine Translation Using LLMs

Khalid Sami, Dipto Sumit, A. H. M. Kishowar Hossain, Farig Sadeque

Translating from a standard language to its regional dialects is a significant NLP challenge due to scarce data and linguistic variation, a problem prominent in the Bengali language. This paper proposes and compares two novel RAG pipelines for standard-to-dialectal Bengali translation. The …

Advancing Bangla Machine Translation Through Informal Datasets

Ayon Roy, Risat Rahaman, Sadat Shibly, Udoy Saha Joy et autres

Bangla is the sixth most widely spoken language globally, with approximately 234 million native speakers. However, progress in open-source Bangla machine translation remains limited. Most online resources are in English and often remain untranslated into Bangla, excluding millions from accessing essential information. …

Is Lying Only Sinful in Islam? Exploring Religious Bias in Multilingual Large Language Models Across Major Religions

Kazi Abrab Hossain, Jannatul Somiya Mahmud, Maria Hossain Tuli, S M Taiabul Haque et autres

While recent developments in large language models have improved bias detection and classification, sensitive subjects like religion still present challenges because even minor errors can result in severe misunderstandings. In particular, multilingual models often misrepresent religions and have difficulties being accurate in …

Transforming Mentorship: An AI Powered Chatbot Approach to University Guidance

Mantaqa abedin, A. M. Selim Reza, Farig Sadeque, Niloy Farhan

University students face immense challenges during their undergraduate lives, often being deprived of personalized on-demand guidance that mentors fail to provide at scale. Digital tools exist, but there is a serious lack of customized coaching for newcomers. This paper presents an AI-powered …

Exploring and Mitigating Gender Bias in Encoder-Based Transformer Models

A. H. M. Kishowar Hossain, Khondokar Mohammad Ahanaf Hannan, Nowreen Tarannum Rafa, Humayra Musarrat et autres

Gender bias in language models has gained increasing attention in the field of natural language processing. Encoder-based transformer models, which have achieved state-of-the-art performance in various language tasks, have been shown to exhibit strong gender biases inherited from their training data. This …

From Facts to Folklore: Evaluating Large Language Models on Bengali Cultural Knowledge

Mst. Mafruha Haque, Nazia Tasnim, Md. Istiak Hossain Shihab, Sajjadur Rahman et autres

Recent progress in NLP research has demonstrated remarkable capabilities of large language models (LLMs) across a wide range of tasks. While recent multilingual benchmarks have advanced cultural evaluation for LLMs, critical gaps remain in capturing the nuances of low-resource cultures. Our work …

A Survey on Agentic Security: Applications, Threats and Defenses

Asif Shahriar, Md. Mostafizur Rahman, Farig Sadeque, Md Rizwan Parvez

LLM-based agents are now used throughout cybersecurity. While these agents facilitate powerful and autonomous security applications, their autonomy opens up new attack surfaces, and the security community is actively building defenses to secure them. Yet the literature on this subject has grown …

BanglaDocAtlas: A Multi-Class Annotated Dataset for Complex Bangla Document Layout Analysis

Md Safayat Hossain, Jannatul Ferdous, Md Raihan Uddin, Khandaker M. Anwar Hossain et autres

Optical Character Recognition (OCR) technology is a vital tool for digitizing printed content, enabling efficient data extraction and enhancing document accessibility. Traditional OCR techniques rely on pre-stored templates for fonts or structured documents. Recent advancements in Machine Learning (ML), particularly Convolutional Neural …

bd, us (code pays fourni par la source)

Eyes on the Image: Gaze Supervised Multimodal Learning for Chest X-ray Diagnosis and Report Generation

Tanjim Islam Riju, Saman Sarker Joy, Farig Sadeque, Swakkhar Shatabda

Medical vision-language models still struggle to match radiologists' attention and to verbalize findings with explicit spatial grounding. We address this gap with a two-stage multimodal framework for chest X-ray interpretation built on the MIMIC-Eye dataset. In the first stage introduces a gaze-token …