15 papers · 1 filter
destroR: A Benchmark and Adversarial-Training Defense for Bangla Transfer Models under Meaning-Preserving Attacks
Saadat Rafid Ahmed, Rubayet Shareen, Radoan Sharkar +3
Transformer-based transfer models now dominate Bangla sentiment classification, yet their adversarial robustness remains largely unexamined, and no prior study pairs a Bangla attac…
Optimizing Abstractive Summarization With Fine-Tuned PEGASUS
Sadiul Arefin Rafi, Naimur Rahman, Kazi Nazibul Islam +2
Abstractive text summarization is the technique of generating a short and concise summary comprising the salient ideas of a source text without making a subset of the salient sente…
A Survey on Agentic Security: Applications, Threats and Defenses
Asif Shahriar, Md Nafiu Rahman, Sadif Ahmed +2
LLM-based agents are now used throughout cybersecurity. While these agents facilitate powerful and autonomous security applications, their autonomy opens up new attack surfaces, an…
Understanding QA generation: Extracting Parametric and Contextual Knowledge with CQA for Low Resource Bangla Language
Umme Abira Azmary, MD Ikramul Kayes, Swakkhar Shatabda +1
Question-Answering (QA) models for low-resource languages like Bangla face challenges due to limited annotated data and linguistic complexity. A key issue is determining whether mo…
A Comparative Analysis of Retrieval-Augmented Generation Techniques for Bengali Standard-to-Dialect Machine Translation Using LLMs
K. M. Jubair Sami, Dipto Sumit, Ariyan Hossain +1
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 languag…
Advancing Bangla Machine Translation Through Informal Datasets
Ayon Roy, Risat Rahaman, Sadat Shibly +3
Bangla is the sixth most widely spoken language globally, with approximately 234 million native speakers. However, progress in open-source Bangla machine translation remains limite…