37 citations · 74 across the 26 of their papers we have counts for
29 papers
Seeing Through the Forgery Is Not Enough: Regressive Sycophancy under Fabricated Evidence in Medical Vision-Language Models
Sadif Ahmed, Soumya Swagata Biswas, Rifat Shahriyar +1
A medical vision-language model may analyze a given CT scan and correctly detect both kidneys in view. Continuing this conversation, if a user provides a prescription with an oppos…
DocTalkBN: A Novel Dataset of Expert Telemedicine Conversations in Bengali
Anik Saha, Fahmida Sultana Naznin, Sadatul Islam Sadi +3
Reliable medical conversational AI requires authentic expert--patient interaction data, yet such datasets remain scarce, especially for low-resource languages such as Bengali. We p…
Rust for Secure Backend Development: A Critical Review and Extended Vulnerability Comparison with Node.js and Django
Md Zarzees Uddin Shah Chowdhury, Rabib Jahin Ibn Momin, Rifat Shahriyar
The Rust programming language is widely credited with eliminating entire classes of memory-safety and concurrency vulnerabilities, but the security implications of adopting it in p…
IssueGuard: Real-Time Secret Leak Prevention Tool for GitHub Issue Reports
Md Nafiu Rahman, Sadif Ahmed, Zahin Wahab +2
GitHub and GitLab are widely used collaborative platforms whose issue-tracking systems contain large volumes of unstructured text, including logs, code snippets, and configuration…
Inceptive Transformers: Enhancing Contextual Representations through Multi-Scale Feature Learning Across Domains and Languages
Asif Shahriar, Rifat Shahriyar, M Saifur Rahman
Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hi…
Secret Breach Detection in Source Code with Large Language Models
Md Nafiu Rahman, Sadif Ahmed, Zahin Wahab +2
Background: Leaking sensitive information - such as API keys, tokens, and credentials - in source code remains a persistent security threat. Traditional regex and entropy-based too…
Multi-ToM: Evaluating Multilingual Theory of Mind Capabilities in Large Language Models
Jayanta Sadhu, Ayan Antik Khan, Noshin Nawal +3
Theory of Mind (ToM) refers to the cognitive ability to infer and attribute mental states to oneself and others. As large language models (LLMs) are increasingly evaluated for soci…
Secret Leak Detection in Software Issue Reports using LLMs: A Comprehensive Evaluation
Sadif Ahmed, Md Nafiu Rahman, Zahin Wahab +2
In the digital era, accidental exposure of sensitive information such as API keys, tokens, and credentials is a growing security threat. While most prior work focuses on detecting…
ChakmaNMT: Machine Translation for a Low-Resource and Endangered Language via Transliteration
Aunabil Chakma, Aditya Chakma, Masum Hasan +3
We present the first systematic study of machine translation for Chakma, an endangered and extremely low-resource Indo-Aryan language, with the goal of supporting language access a…
ConVerSum: A Contrastive Learning-based Approach for Data-Scarce Solution of Cross-Lingual Summarization Beyond Direct Equivalents
Sanzana Karim Lora, M. Sohel Rahman, Rifat Shahriyar
Cross-lingual summarization (CLS) is a sophisticated branch in Natural Language Processing that demands models to accurately translate and summarize articles from different source…
An Empirical Study of Gendered Stereotypes in Emotional Attributes for Bangla in Multilingual Large Language Models
Jayanta Sadhu, Maneesha Rani Saha, Rifat Shahriyar
The influence of Large Language Models (LLMs) is rapidly growing, automating more jobs over time. Assessing the fairness of LLMs is crucial due to their expanding impact. Studies r…
Social Bias in Large Language Models For Bangla: An Empirical Study on Gender and Religious Bias
Jayanta Sadhu, Maneesha Rani Saha, Rifat Shahriyar
The rapid growth of Large Language Models (LLMs) has put forward the study of biases as a crucial field. It is important to assess the influence of different types of biases embedd…
An Empirical Study on the Characteristics of Bias upon Context Length Variation for Bangla
Jayanta Sadhu, Ayan Antik Khan, Abhik Bhattacharjee +1
Pretrained language models inherently exhibit various social biases, prompting a crucial examination of their social impact across various linguistic contexts due to their widespre…
IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models
Haz Sameen Shahgir, Khondker Salman Sayeed, Abhik Bhattacharjee +3
The advent of Vision Language Models (VLM) has allowed researchers to investigate the visual understanding of a neural network using natural language. Beyond object classification…
BanglaParaphrase: A High-Quality Bangla Paraphrase Dataset
Ajwad Akil, Najrin Sultana, Abhik Bhattacharjee +1
In this work, we present BanglaParaphrase, a high-quality synthetic Bangla Paraphrase dataset curated by a novel filtering pipeline. We aim to take a step towards alleviating the l…
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran +74
Evaluation in machine learning is usually informed by past choices, for example which datasets or metrics to use. This standardization enables the comparison on equal footing using…
BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla
Abhik Bhattacharjee, Tahmid Hasan, Wasi Uddin Ahmad +1
This work presents BanglaNLG, a comprehensive benchmark for evaluating natural language generation (NLG) models in Bangla, a widely spoken yet low-resource language. We aggregate s…
A Crowd-enabled Solution for Privacy-Preserving and Personalized Safe Route Planning for Fixed or Flexible Destinations (Full Version)
Fariha Tabassum Islam, Tanzima Hashem, Rifat Shahriyar
Ensuring travelers' safety on roads has become a research challenge in recent years. We introduce a novel safe route planning problem and develop an efficient solution to ensure th…
CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs
Abhik Bhattacharjee, Tahmid Hasan, Wasi Uddin Ahmad +3
We present CrossSum, a large-scale cross-lingual summarization dataset comprising 1.68 million article-summary samples in 1,500+ language pairs. We create CrossSum by aligning para…
A Survey-Based Qualitative Study to Characterize Expectations of Software Developers from Five Stakeholders
Khalid Hasan, Partho Chakraborty, Rifat Shahriyar +2
Background: Studies on developer productivity and well-being find that the perceptions of productivity in a software team can be a socio-technical problem. Intuitively, problems an…
XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages
Tahmid Hasan, Abhik Bhattacharjee, Md Saiful Islam +5
Contemporary works on abstractive text summarization have focused primarily on high-resource languages like English, mostly due to the limited availability of datasets for low/mid-…
CoDesc: A Large Code-Description Parallel Dataset
Masum Hasan, Tanveer Muttaqueen, Abdullah Al Ishtiaq +6
Translation between natural language and source code can help software development by enabling developers to comprehend, ideate, search, and write computer programs in natural lang…
How do developers discuss and support new programming languages in technical Q&A site? An empirical study of Go, Swift, and Rust in Stack Overflow
Partha Chakraborty, Rifat Shahriyar, Anindya Iqbal +1
New programming languages (e.g., Swift, Go, Rust, etc.) are being introduced to provide a better opportunity for the developers to make software development robust and easy. At the…
BERT2Code: Can Pretrained Language Models be Leveraged for Code Search?
Abdullah Al Ishtiaq, Masum Hasan, Md. Mahim Anjum Haque +5
Millions of repetitive code snippets are submitted to code repositories every day. To search from these large codebases using simple natural language queries would allow programmer…