collaborators

8 papers

cs.CL2025

Distinguishing Repetition Disfluency from Morphological Reduplication in Bangla ASR Transcripts: A Novel Corpus and Benchmarking Analysis

Zaara Zabeen Arpa, Sadnam Sakib Apurbo, Nazia Karim Khan Oishee +1

Automatic Speech Recognition (ASR) transcripts, especially in low-resource languages like Bangla, contain a critical ambiguity: word-word repetitions can be either Repetition Disfl…

cs.CL2025

Faithful Summarization of Consumer Health Queries: A Cross-Lingual Framework with LLMs

Ajwad Abrar, Nafisa Tabassum Oeshy, Prianka Maheru +2

Summarizing consumer health questions (CHQs) can ease communication in healthcare, but unfaithful summaries that misrepresent medical details pose serious risks. We propose a frame…

cs.CL2025

BanglaMedQA and BanglaMMedBench: Evaluating Retrieval-Augmented Generation Strategies for Bangla Biomedical Question Answering

Sadia Sultana, Saiyma Sittul Muna, Mosammat Zannatul Samarukh +2

Developing accurate biomedical Question Answering (QA) systems in low-resource languages remains a major challenge, limiting equitable access to reliable medical knowledge. This pa…

cs.CL2025

FirstAidQA: A Synthetic Dataset for First Aid and Emergency Response in Low-Connectivity Settings

Saiyma Sittul Muna, Rezwan Islam Salvi, Mushfiqur Rahman Mushfique +1

In emergency situations, every second counts. The deployment of Large Language Models (LLMs) in time-sensitive, low or zero-connectivity environments remains limited. Current model…

cs.CL2025

From Chat to Checkup: Can Large Language Models Assist in Diabetes Prediction?

Shadman Sakib, Oishy Fatema Akhand, Ajwad Abrar

While Machine Learning (ML) and Deep Learning (DL) models have been widely used for diabetes prediction, the use of Large Language Models (LLMs) for structured numerical data is st…

cs.CL2025

Performance Evaluation of Large Language Models in Bangla Consumer Health Query Summarization

Ajwad Abrar, Farzana Tabassum, Sabbir Ahmed

Consumer Health Queries (CHQs) in Bengali (Bangla), a low-resource language, often contain extraneous details, complicating efficient medical responses. This study investigates the…