arXiv subjects

Swastika Kundu

Publications and source records attributed to Swastika Kundu.

3 recordsLinked to original sources

arXiv2026

PatiGonit22K: A Comprehensive Dataset for Solving Complex Bengali MWPs

Mathematical Word Problems (MWPs) are an important benchmark for evaluating natural language understanding and quantitative reasoning. Despite recent progress in high resource languages, Bengali remains underexplored due to the limited availability of large scale annotated datasets. In this work, we introduce PatiGonit22K, an expanded Bengali MWP dataset containing 22,441 problems, developed by extending the original PatiGonit dataset with a substantially larger collection of complex mathematical problems. The dataset includes both simple and multi operation equations, providing a balanced benchmark for evaluating mathematical reasoning across different difficulty levels. Each problem is carefully translated, annotated, culturally adapted, and verified to ensure linguistic consistency and mathematical correctness. By increasing both the scale and complexity of Bengali MWPs, PatiGonit22K provides a more comprehensive resource for future research on mathematical reasoning and educational NLP applications in low resource languages.

cs.CL↗

arXiv2026

GSM-Plus-BN: A Perturbation-Based Benchmark for Bangla Mathematical Reasoning in Large Language Models

The evaluation of mathematical reasoning in large language models (LLMs) has predominantly focused on high-resource languages like English. This has created a significant barrier to the equitable development and deployment of AI in linguistically diverse regions such as Bangladesh, where over 230 million people speak Bengali. Despite this global significance, there has been minimal prior work on mathematical reasoning in Bengali and no existing research that systematically benchmarks a perturbated Bengali mathematical dataset, leaving a critical void in assessing model robustness and true comprehension beyond pattern recognition. This study addresses this gap by introducing GSM-Plus-BN, a novel perturbated Bengali mathematical dataset derived from the English GSM-Plus benchmark and verified by human translators. We evaluate six open-source LLMs Qwen3-32B, Llama-3.1-8B-Instant, Llama-3.3-70B-Versatile, Llama-4-Scout-17B-16E-Instruct, GPT-OSS-120B, and GPT-OSS-20B using a benchmark of 9,000 evaluation samples comprising 1,000 seed questions and 8,000 perturbed variants under both Standard Prompting and Chain-of-Thought (CoT) Prompting. Experimental results show that GPT-OSS-20B achieves the highest seed question accuracy of 96.08% under Standard Prompting, while larger models such as Llama-3.3-70B and GPT-OSS-120B demonstrate superior robustness across perturbation types. Furthermore, CoT prompting substantially improves reasoning for most models compared to Standard Prompting, yet a notable performance gap persists across all models relative to their English benchmarks, underscoring the inherent difficulty of perturbed Bengali text. This research makes a foundational contribution by providing GSM-PLUS-BN as a new resource and baseline for future Bengali mathematical reasoning research.

cs.CL↗

arXiv2026

ANUBHUTI: A Comprehensive Corpus For Sentiment Analysis In Bangla Regional Languages

Sentiment analysis for regional dialects of Bangla remains an underexplored area due to linguistic diversity and limited annotated data. This paper introduces ANUBHUTI, a comprehensive dataset consisting of 10,000 sentences manually translated from standard Bangla into four major regional dialects Mymensingh, Noakhali, Sylhet, and Chittagong. The dataset predominantly features political and religious content, reflecting the contemporary socio political landscape of Bangladesh, alongside neutral texts to maintain balance. Each sentence is annotated using a dual annotation scheme: multiclass thematic labeling categorizes sentences as Political, Religious, or Neutral, and multilabel emotion annotation assigns one or more emotions from Anger, Contempt, Disgust, Enjoyment, Fear, Sadness, and Surprise. Expert native translators conducted the translation and annotation, with quality assurance performed via Cohens Kappa inter annotator agreement, achieving strong consistency across dialects. The dataset was further refined through systematic checks for missing data, anomalies, and inconsistencies. ANUBHUTI fills a critical gap in resources for sentiment analysis in low resource Bangla dialects, enabling more accurate and context aware natural language processing.

cs.CL↗