arXiv subjects

Swakkhar Shatabda

Publications and source records attributed to Swakkhar Shatabda.

At least 37 records · Page 2Linked to original sources

arXiv2026

Understanding QA generation: Extracting Parametric and Contextual Knowledge with CQA for Low Resource Bangla Language

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 models rely more on pre-encoded (parametric) knowledge or contextual input during answer generation, as existing Bangla QA datasets lack the structure required for such analysis. We introduce BanglaCQA, the first Counterfactual QA dataset in Bangla, by extending a Bangla dataset while integrating counterfactual passages and answerability annotations. In addition, we propose fine-tuned pipelines for encoder-decoder language-specific and multilingual baseline models, and prompting-based pipelines for decoder-only LLMs to disentangle parametric and contextual knowledge in both factual and counterfactual scenarios. Furthermore, we apply LLM-based and human evaluation techniques that measure answer quality based on semantic similarity. We also present a detailed analysis of how models perform across different QA settings in low-resource languages, and show that Chain-of-Thought (CoT) prompting reveals a uniquely effective mechanism for extracting parametric knowledge in counterfactual scenarios, particularly in decoder-only LLMs. Our work not only introduces a novel framework for analyzing knowledge sources in Bangla QA but also uncovers critical findings that open up broader directions for counterfactual reasoning in low-resource language settings.

cs.CL↗

arXiv2026

MathMist: A Parallel Multilingual Benchmark Dataset for Mathematical Problem Solving and Reasoning

Mathematical reasoning remains one of the most challenging domains for large language models (LLMs), requiring not only linguistic understanding but also structured logical deduction and numerical precision. While recent LLMs demonstrate strong general-purpose reasoning abilities, their mathematical competence across diverse languages remains underexplored. Existing benchmarks primarily focus on English or a narrow subset of high-resource languages, leaving significant gaps in assessing multilingual and cross-lingual mathematical reasoning. To address this, we introduce MATHMIST, a parallel multilingual benchmark for mathematical problem solving and reasoning. MATHMIST encompasses 2,890 parallel Bangla-English gold standard artifacts, totaling approximately 30K aligned question--answer pairs across thirteen languages, representing an extensive coverage of high-, medium-, and low-resource linguistic settings. The dataset captures linguistic variety, multiple types of problem settings, and solution synthesizing capabilities. We systematically evaluate a diverse suite of models, including open-source small and medium LLMs, proprietary systems, and multilingual-reasoning-focused models under zero-shot, chain-of-thought (CoT), perturbated reasoning, and code-switched reasoning paradigms. Our results reveal persistent deficiencies in LLMs' ability to perform consistent and interpretable mathematical reasoning across languages, with pronounced degradation in low-resource settings. All the codes and data are available at GitHub: https://github.com/mahbubhimel/MathMist

cs.CL↗

arXiv2026

BnMMLU: Measuring Massive Multitask Language Understanding in Bengali

Large-scale multitask benchmarks have driven rapid progress in language modeling, yet most emphasize high-resource languages such as English, leaving Bengali underrepresented. We present BnMMLU, a comprehensive benchmark for measuring massive multitask language understanding in Bengali. BnMMLU spans 41 domains across STEM, humanities, social sciences, and general knowledge, and contains 134,375 multiple-choice question-option pairs--the most extensive Bengali evaluation suite to date. The dataset preserves mathematical content via MathML, and includes BnMMLU-HARD, a compact subset constructed from questions most frequently missed by top systems to stress difficult cases. We benchmark 24 model variants across 11 LLM families, spanning open-weights general/multilingual, Bengali-centric open-weights, and proprietary models, covering multiple parameter scales and instruction-tuned settings. We evaluate models under standardized protocols covering two prompting styles (Direct vs. Chain-of-Thought) and two context regimes (0-shot vs. 5-shot), reporting accuracy consistently across families. Our analysis highlights persistent gaps in reasoning and application skills and indicates sublinear returns to scale across model sizes. We release the dataset and evaluation templates to support rigorous, reproducible assessment of Bengali language understanding and to catalyze progress in multilingual NLP.

cs.CL↗

arXiv2025

Can LLMs Solve My Grandma's Riddle? Evaluating Multilingual Large Language Models on Reasoning Traditional Bangla Tricky Riddles

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 underexplored. We address this gap for Bangla by introducing BanglaRiddleEval, a benchmark of 1,244 traditional Bangla riddles instantiated across four tasks (4,976 riddle-task artifacts in total). Using an LLM-based pipeline, we generate Chain-of-Thought explanations, semantically coherent distractors, and fine-grained ambiguity annotations, and evaluate a diverse suite of open-source and closed-source models under different prompting strategies. Models achieve moderate semantic overlap on generative QA but low correctness, MCQ accuracy peaks at only about 56% versus an 83% human baseline, and ambiguity resolution ranges from roughly 26% to 68%, with high-quality explanations confined to the strongest models. These results show that current LLMs capture some cues needed for Bangla riddle reasoning but remain far from human-level performance, establishing BanglaRiddleEval as a challenging new benchmark for low-resource figurative reasoning. All data, code, and evaluation scripts are available on GitHub: https://github.com/Labib1610/BanglaRiddleEval.

cs.CL↗

arXiv2025

Do Multi-Agents Solve Better Than Single? Evaluating Agentic Frameworks for Diagram-Grounded Geometry Problem Solving and Reasoning

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 unclear. We systematically compare single-agent and multi-agent pipelines on four visual math benchmarks: Geometry3K, MathVerse, OlympiadBench, and We-Math. For open-source models, multi-agent consistently improves performance. For example, Qwen-2.5-VL (7B) gains +6.8 points and Qwen-2.5-VL (32B) gains +3.3 on Geometry3K, and both Qwen-2.5-VL variants see further gains on OlympiadBench and We-Math. In contrast, the closed-source Gemini-2.0-Flash generally performs better in single-agent mode on classic benchmarks, while multi-agent yields only modest improvements on the newer We-Math dataset. These findings show that multi-agent pipelines provide clear benefits for open-source models and can assist strong proprietary systems on newer, less familiar benchmarks, but agentic decomposition is not universally optimal. All code, data, and reasoning files are available at https://github.com/faiyazabdullah/Interpreter-Solver

cs.AI↗

arXiv2025

Ready to Translate, Not to Represent? Bias and Performance Gaps in Multilingual LLMs Across Language Families and Domains

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. Despite their remarkable capabilities, LLMs often exhibit uneven performance across language families and specialized domains. Moreover, recent evidence reveals that these models can encode and amplify different biases present in their training data, posing serious concerns for fairness, especially in low-resource languages. To address these gaps, we introduce Translation Tangles, a unified framework and dataset for evaluating the translation quality and fairness of open-source LLMs. Our approach benchmarks 24 bidirectional language pairs across multiple domains using different metrics. We further propose a hybrid bias detection pipeline that integrates rule-based heuristics, semantic similarity filtering, and LLM-based validation. We also introduce a high-quality, bias-annotated dataset based on human evaluations of 1,439 translation-reference pairs. The code and dataset are accessible on GitHub: https://github.com/faiyazabdullah/TranslationTangles

cs.CL↗

arXiv2025

Embedding Is (Almost) All You Need: Retrieval-Augmented Inference for Generalizable Genomic Prediction Tasks

Large pre-trained DNA language models such as DNABERT-2, Nucleotide Transformer, and HyenaDNA have demonstrated strong performance on various genomic benchmarks. However, most applications rely on expensive fine-tuning, which works best when the training and test data share a similar distribution. In this work, we investigate whether task-specific fine-tuning is always necessary. We show that simple embedding-based pipelines that extract fixed representations from these models and feed them into lightweight classifiers can achieve competitive performance. In evaluation settings with different data distributions, embedding-based methods often outperform fine-tuning while reducing inference time by 10x to 20x. Our results suggest that embedding extraction is not only a strong baseline but also a more generalizable and efficient alternative to fine-tuning, especially for deployment in diverse or unseen genomic contexts. For example, in enhancer classification, HyenaDNA embeddings combined with zCurve achieve 0.68 accuracy (vs. 0.58 for fine-tuning), with an 88% reduction in inference time and over 8x lower carbon emissions (0.02 kg vs. 0.17 kg CO2). In non-TATA promoter classification, DNABERT-2 embeddings with zCurve or GC content reach 0.85 accuracy (vs. 0.89 with fine-tuning) with a 22x lower carbon footprint (0.02 kg vs. 0.44 kg CO2). These results show that embedding-based pipelines offer over 10x better carbon efficiency while maintaining strong predictive performance. The code is available here: https://github.com/NIRJHOR-DATTA/EMBEDDING-IS-ALMOST-ALL-YOU-NEED.

q-bio.GN↗

arXiv2025

Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation

Multimodal Large Language Models (MLLMs) are increasingly used for content moderation, yet their robustness in short-form video contexts remains underexplored. Current safety evaluations often rely on unimodal attacks, failing to address combined attack vulnerabilities. In this paper, we introduce a comprehensive framework for evaluating the tri-modal safety of MLLMs. First, we present the Short-Video Multimodal Adversarial (SVMA) dataset, comprising diverse short-form videos with human-guided synthetic adversarial attacks. Second, we propose ChimeraBreak, a novel tri-modal attack strategy that simultaneously challenges visual, auditory, and semantic reasoning pathways. Extensive experiments on state-of-the-art MLLMs reveal significant vulnerabilities with high Attack Success Rates (ASR). Our findings uncover distinct failure modes, showing model biases toward misclassifying benign or policy-violating content. We assess results using LLM-as-a-judge, demonstrating attack reasoning efficacy. Our dataset and findings provide crucial insights for developing more robust and safe MLLMs.

cs.CV↗

arXiv2025

TritonZ: A Remotely Operated Underwater Rover with Manipulator Arm for Exploration and Rescue Operations

The increasing demand for underwater exploration and rescue operations enforces the development of advanced wireless or semi-wireless underwater vessels equipped with manipulator arms. This paper presents the implementation of a semi-wireless underwater vehicle, "TritonZ" equipped with a manipulator arm, tailored for effective underwater exploration and rescue operations. The vehicle's compact design enables deployment in different submarine surroundings, addressing the need for wireless systems capable of navigating challenging underwater terrains. The manipulator arm can interact with the environment, allowing the robot to perform sophisticated tasks during exploration and rescue missions in emergency situations. TritonZ is equipped with various sensors such as Pi-Camera, Humidity, and Temperature sensors to send real-time environmental data. Our underwater vehicle controlled using a customized remote controller can navigate efficiently in the water where Pi-Camera enables live streaming of the surroundings. Motion control and video capture are performed simultaneously using this camera. The manipulator arm is designed to perform various tasks, similar to grasping, manipulating, and collecting underwater objects. Experimental results shows the efficacy of the proposed remotely operated vehicle in performing a variety of underwater exploration and rescue tasks. Additionally, the results show that TritonZ can maintain an average of 13.5cm/s with a minimal delay of 2-3 seconds. Furthermore, the vehicle can sustain waves underwater by maintaining its position as well as average velocity. The full project details and source code can be accessed at this link: https://github.com/kawser-ahmed-byte/TritonZ

cs.RO↗

arXiv2025

HingeRLC-GAN: Combating Mode Collapse with Hinge Loss and RLC Regularization

Recent advances in Generative Adversarial Networks (GANs) have demonstrated their capability for producing high-quality images. However, a significant challenge remains mode collapse, which occurs when the generator produces a limited number of data patterns that do not reflect the diversity of the training dataset. This study addresses this issue by proposing a number of architectural changes aimed at increasing the diversity and stability of GAN models. We start by improving the loss function with Wasserstein loss and Gradient Penalty to better capture the full range of data variations. We also investigate various network architectures and conclude that ResNet significantly contributes to increased diversity. Building on these findings, we introduce HingeRLC-GAN, a novel approach that combines RLC Regularization and the Hinge loss function. With a FID Score of 18 and a KID Score of 0.001, our approach outperforms existing methods by effectively balancing training stability and increased diversity.

cs.LG↗

arXiv2025

Design of a Microprocessors and Microcontrollers Laboratory Course Addressing Complex Engineering Problems and Activities

This paper proposes a novel curriculum for the microprocessors and microcontrollers laboratory course. The proposed curriculum blends structured laboratory experiments with an open-ended project phase, addressing complex engineering problems and activities. Microprocessors and microcontrollers are ubiquitous in modern technology, driving applications across diverse fields. To prepare future engineers for Industry 4.0, effective educational approaches are crucial. The proposed lab enables students to perform hands-on experiments using advanced microprocessors and microcontrollers while leveraging their acquired knowledge by working in teams to tackle self-defined complex engineering problems that utilize these devices and sensors, often used in the industry. Furthermore, this curriculum fosters multidisciplinary learning and equips students with problem-solving skills that can be applied in real-world scenarios. With recent technological advancements, traditional microprocessors and microcontrollers curricula often fail to capture the complexity of real-world applications. This curriculum addresses this critical gap by incorporating insights from experts in both industry and academia. It trains students with the necessary skills and knowledge to thrive in this rapidly evolving technological landscape, preparing them for success upon graduation. The curriculum integrates project-based learning, where students define complex engineering problems for themselves. This approach actively engages students, fostering a deeper understanding and enhancing their learning capabilities. Statistical analysis shows that the proposed curriculum significantly improves student learning outcomes, particularly in their ability to formulate and solve complex engineering problems, as well as engage in complex engineering activities.

cs.CY↗

arXiv2025

FeatPCA: A feature subspace based principal component analysis technique for enhancing clustering of single-cell RNA-seq data

Single-cell RNA sequencing (scRNA-seq) has revolutionized our ability to analyze gene expression at the cellular level. By providing data on gene expression for each individual cell, scRNA-seq generates large datasets with thousands of genes. However, handling such high-dimensional data poses computational challenges due to increased complexity. Dimensionality reduction becomes crucial for scRNA-seq analysis. Various dimensionality reduction algorithms, including Principal Component Analysis (PCA), Uniform Manifold Approximation and Projection (UMAP), and t-Distributed Stochastic Neighbor Embedding (t-SNE), are commonly used to address this challenge. These methods transform the original high-dimensional data into a lower-dimensional representation while preserving relevant information. In this paper we propose {\methodname}. Instead of applying dimensionality reduction directly to the entire dataset, we divide it into multiple subspaces. Within each subspace, we apply dimension reduction techniques, and then merge the reduced data. {\methodname} offers four variations for subspacing. Our experimental results demonstrate that clustering based on subspacing yields better accuracy than working with the full dataset. Across a variety of scRNA-seq datasets, {\methodname} consistently outperforms existing state-of-the-art clustering tools.

cs.CC↗

arXiv2024

Adaptive Tabu Dropout for Regularization of Deep Neural Network

Dropout is an effective strategy for the regularization of deep neural networks. Applying tabu to the units that have been dropped in the recent epoch and retaining them for training ensures diversification in dropout. In this paper, we improve the Tabu Dropout mechanism for training deep neural networks in two ways. Firstly, we propose to use tabu tenure, or the number of epochs a particular unit will not be dropped. Different tabu tenures provide diversification to boost the training of deep neural networks based on the search landscape. Secondly, we propose an adaptive tabu algorithm that automatically selects the tabu tenure based on the training performances through epochs. On several standard benchmark datasets, the experimental results show that the adaptive tabu dropout and tabu tenure dropout diversify and perform significantly better compared to the standard dropout and basic tabu dropout mechanisms.

cs.LG↗

arXiv2024

BanglishRev: A Large-Scale Bangla-English and Code-mixed Dataset of Product Reviews in E-Commerce

This work presents the BanglishRev Dataset, the largest e-commerce product review dataset to date for reviews written in Bengali, English, a mixture of both and Banglish, Bengali words written with English alphabets. The dataset comprises of 1.74 million written reviews from 3.2 million ratings information collected from a total of 128k products being sold in online e-commerce platforms targeting the Bengali population. It includes an extensive array of related metadata for each of the reviews including the rating given by the reviewer, date the review was posted and date of purchase, number of likes, dislikes, response from the seller, images associated with the review etc. With sentiment analysis being the most prominent usage of review datasets, experimentation with a binary sentiment analysis model with the review rating serving as an indicator of positive or negative sentiment was conducted to evaluate the effectiveness of the large amount of data presented in BanglishRev for sentiment analysis tasks. A BanglishBERT model is trained on the data from BanglishRev with reviews being considered labeled positive if the rating is greater than 3 and negative if the rating is less than or equal to 3. The model is evaluated by being testing against a previously published manually annotated dataset for e-commerce reviews written in a mixture of Bangla, English and Banglish. The experimental model achieved an exceptional accuracy of 94\% and F1 score of 0.94, demonstrating the dataset's efficacy for sentiment analysis. Some of the intriguing patterns and observations seen within the dataset and future research directions where the dataset can be utilized is also discussed and explored. The dataset can be accessed through https://huggingface.co/datasets/BanglishRev/bangla-english-and-code-mixed-ecommerce-review-dataset.

cs.CL↗

arXiv2024

An Enhanced Text Compression Approach Using Transformer-based Language Models

Text compression shrinks textual data while keeping crucial information, eradicating constraints on storage, bandwidth, and computational efficacy. The integration of lossless compression techniques with transformer-based text decompression has received negligible attention, despite the increasing volume of English text data in communication. The primary barrier in advancing text compression and restoration involves optimizing transformer-based approaches with efficient pre-processing and integrating lossless compression algorithms, that remained unresolved in the prior attempts. Here, we propose a transformer-based method named RejuvenateForme for text decompression, addressing prior issues by harnessing a new pre-processing technique and a lossless compression method. Our meticulous pre-processing technique incorporating the Lempel-Ziv-Welch algorithm achieves compression ratios of 12.57, 13.38, and 11.42 on the BookCorpus, EN-DE, and EN-FR corpora, thus showing state-of-the-art compression ratios compared to other deep learning and traditional approaches. Furthermore, the RejuvenateForme achieves a BLEU score of 27.31, 25.78, and 50.45 on the EN-DE, EN-FR, and BookCorpus corpora, showcasing its comprehensive efficacy. In contrast, the pre-trained T5-Small exhibits better performance over prior state-of-the-art models.

cs.CL↗

arXiv2024

Accurate Water Level Monitoring in AWD Rice Cultivation Using Convolutional Neural Networks

The Alternate Wetting and Drying (AWD) method is a rice-growing water management technique promoted as a sustainable alternative to Continuous Flooding (CF). Climate change has placed the agricultural sector in a challenging position, particularly as global water resources become increasingly scarce, affecting rice production on irrigated lowlands. Rice, a staple food for over half of the world's population, demands significantly more water than other major crops. In Bangladesh, Boro rice, in particular, requires considerable water inputs during its cultivation. Traditionally, farmers manually measure water levels, a process that is both time-consuming and prone to errors. While ultrasonic sensors offer improvements in water height measurement, they still face limitations, such as susceptibility to weather conditions and environmental factors. To address these issues, we propose a novel approach that automates water height measurement using computer vision, specifically through a convolutional neural network (CNN). Our attention-based architecture achieved an $R^2$ score of 0.9885 and a Mean Squared Error (MSE) of 0.2766, providing a more accurate and efficient solution for managing AWD systems.

cs.CV↗

arXiv2024

A Bidirectional Siamese Recurrent Neural Network for Accurate Gait Recognition Using Body Landmarks

Gait recognition is a significant biometric technique for person identification, particularly in scenarios where other physiological biometrics are impractical or ineffective. In this paper, we address the challenges associated with gait recognition and present a novel approach to improve its accuracy and reliability. The proposed method leverages advanced techniques, including sequential gait landmarks obtained through the Mediapipe pose estimation model, Procrustes analysis for alignment, and a Siamese biGRU-dualStack Neural Network architecture for capturing temporal dependencies. Extensive experiments were conducted on large-scale cross-view datasets to demonstrate the effectiveness of the approach, achieving high recognition accuracy compared to other models. The model demonstrated accuracies of 95.7%, 94.44%, 87.71%, and 86.6% on CASIA-B, SZU RGB-D, OU-MVLP, and Gait3D datasets respectively. The results highlight the potential applications of the proposed method in various practical domains, indicating its significant contribution to the field of gait recognition.

cs.CV↗

arXiv2024

DPCSpell: A Transformer-based Detector-Purificator-Corrector Framework for Spelling Error Correction of Bangla and Resource Scarce Indic Languages

Spelling error correction is the task of identifying and rectifying misspelled words in texts. It is a potential and active research topic in Natural Language Processing because of numerous applications in human language understanding. The phonetically or visually similar yet semantically distinct characters make it an arduous task in any language. Earlier efforts on spelling error correction in Bangla and resource-scarce Indic languages focused on rule-based, statistical, and machine learning-based methods which we found rather inefficient. In particular, machine learning-based approaches, which exhibit superior performance to rule-based and statistical methods, are ineffective as they correct each character regardless of its appropriateness. In this paper, we propose a novel detector-purificator-corrector framework, DPCSpell based on denoising transformers by addressing previous issues. In addition to that, we present a method for large-scale corpus creation from scratch which in turn resolves the resource limitation problem of any left-to-right scripted language. The empirical outcomes demonstrate the effectiveness of our approach, which outperforms previous state-of-the-art methods by attaining an exact match (EM) score of 94.78%, a precision score of 0.9487, a recall score of 0.9478, an f1 score of 0.948, an f0.5 score of 0.9483, and a modified accuracy (MA) score of 95.16% for Bangla spelling error correction. The models and corpus are publicly available at https://tinyurl.com/DPCSpell.

cs.CL↗