14 papers
Entropy-Gated Dynamic Rectification for Object Hallucination in Large Vision-Language Models
Riasad Alvi, Md. Asaduzzaman Shuvo, Md. Ahashan Habib +1
Large Vision-Language Models (LVLMs) routinely name objects that are absent from the image. Latent steering can reduce this failure in one model forward pass, but a fixed gate trea…
Teach Yourself Where to Look: On-Policy Attention Self-Distillation for Reasoning
Safaeid Hossain Arib, Rabeya Akter, Ismam Nur Swapnil +3
On-policy self-distillation trains reasoning models on their own trajectories using dense token distribution guidance from a privileged teacher with access to a verified solution.…
To What Extent Do Large Language Models Understand Bangla Idioms?
Mousumi Akter, Md. Faiyaz Abdullah Sayeedi, Nurul Labib Sayeedi +1
Idiomatic expressions are an integral part of natural language, reflecting cultural nuances and posing unique challenges for computational models, particularly in low-resource lang…
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…
Do Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context Manifolds
Md. Faiyaz Abdullah Sayeedi
Large Language Models (LLMs) demonstrate remarkable multi-hop reasoning capabilities over long contexts, yet the internal mechanisms enabling these distant cognitive leaps remain p…
MultiHaluDet: Multilingual Hallucination Detection via LLM Hidden State Probing
Riasad Alvi, Nurul Labib Sayeedi, Md. Faiyaz Abdullah Sayeedi
Hallucinations in Large Language Models (LLMs) represent a critical barrier to their reliable deployment, a vulnerability heavily exacerbated in non-English and resource-constraine…
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…
Route, Retrieve, Reflect, Repair: Self-Improving Agentic Framework for Visual Detection and Linguistic Reasoning in Medical Imaging
Md. Faiyaz Abdullah Sayeedi, Rashedur Rahman, Siam Tahsin Bhuiyan +4
Medical image analysis increasingly relies on large vision-language models (VLMs), yet most systems remain single-pass black boxes that offer limited control over reasoning, safety…
Can LLMs Solve My Grandma's Riddle? Evaluating Multilingual Large Language Models on Reasoning Traditional Bangla Tricky Riddles
Nurul Labib Sayeedi, Md. Faiyaz Abdullah Sayeedi, Khushnur Binte Jahangir +2
Large Language Models (LLMs) show impressive performance on many NLP benchmarks, yet their ability to reason in figurative, culturally grounded, and low-resource settings remains u…
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…
Ready to Translate, Not to Represent? Bias and Performance Gaps in Multilingual LLMs Across Language Families and Domains
Md. Faiyaz Abdullah Sayeedi, Md. Mahbub Alam, Subhey Sadi Rahman +5
The rise of Large Language Models (LLMs) has redefined Machine Translation (MT), enabling context-aware and fluent translations across hundreds of languages and textual domains. De…
Rethinking Search: A Study of University Students' Perspectives on Using LLMs and Traditional Search Engines in Academic Problem Solving
Md. Faiyaz Abdullah Sayeedi, Md. Sadman Haque, Zobaer Ibn Razzaque +2
With the increasing integration of Artificial Intelligence (AI) in academic problem solving, university students frequently alternate between traditional search engines like Google…
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…
VisText-Mosquito: A Unified Multimodal Dataset for Visual Detection, Segmentation, and Textual Explanation on Mosquito Breeding Sites
Md. Adnanul Islam, Md. Faiyaz Abdullah Sayeedi, Md. Asaduzzaman Shuvo +3
Mosquito-borne diseases pose a major global health risk, requiring early detection and proactive control of breeding sites to prevent outbreaks. In this paper, we present VisText-M…