5 papers
Time Present and Time Past: Benchmarking Large Language Models on Temporally Evolving Document Understanding
Mahbub E Sobhani, Md. Faiyaz Abdullah Sayeedi, Fahmid Hasan Chowdhury +4
Evolving documents, such as laws, tax codes, and software documentation, are amended, replaced, and sometimes reverted over time, so a question has different correct answers at dif…
TextEconomizer: Enhancing Lossy Text Compression with Denoising Transformers and Entropy Coding
Mahbub E Sobhani, Anika Tasnim Rodela, Chowdhury Mofizur Rahman +2
Lossy text compression reduces data size while preserving core meaning, making it well-suited for summarization, automated analysis, and digital archives. Despite the dominance of…
Many Dialects, Many Languages, One Cultural Lens: Evaluating Multilingual VLMs for Bengali Culture Understanding Across Historically Linked Languages and Regional Dialects
Nurul Labib Sayeedi, Md. Faiyaz Abdullah Sayeedi, Shubhashis Roy Dipta +6
Bangla culture is richly expressed through region, dialect, history, food, politics, media, and everyday visual life, yet it remains underrepresented in multimodal evaluation. To a…
MathMist: A Parallel Multilingual Benchmark Dataset for Mathematical Problem Solving and Reasoning
Mahbub E Sobhani, Md. Faiyaz Abdullah Sayeedi, Tasnim Mohiuddin +2
Mathematical reasoning remains one of the most challenging domains for large language models (LLMs), requiring not only linguistic understanding but also structured logical deducti…
Do Multi-Agents Solve Better Than Single? Evaluating Agentic Frameworks for Diagram-Grounded Geometry Problem Solving and Reasoning
Mahbub E Sobhani, Md. Faiyaz Abdullah Sayeedi, Mohammad Nehad Alam +2
Diagram-grounded geometry problem solving is a critical benchmark for multimodal large language models (MLLMs), yet the benefits of multi-agent design over single-agent remain uncl…