Leveraging Large Language Models for Bengali Math Word Problem Solving with Chain of Thought Reasoning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Paul, Bidyarthi, Era, Jalisha Jashim, Zim, Mirazur Rahman, Aothoi, Tahmid Sattar, Shah, Faisal Muhammad
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913965561348096
author Paul, Bidyarthi
Era, Jalisha Jashim
Zim, Mirazur Rahman
Aothoi, Tahmid Sattar
Shah, Faisal Muhammad
author_facet Paul, Bidyarthi
Era, Jalisha Jashim
Zim, Mirazur Rahman
Aothoi, Tahmid Sattar
Shah, Faisal Muhammad
contents Solving Bengali Math Word Problems (MWPs) remains a major challenge in natural language processing (NLP) due to the language's low-resource status and the multi-step reasoning required. Existing models struggle with complex Bengali MWPs, largely because no human-annotated Bengali dataset has previously addressed this task. This gap has limited progress in Bengali mathematical reasoning. To address this, we created SOMADHAN, a dataset of 8792 complex Bengali MWPs with manually written, step-by-step solutions. We designed this dataset to support reasoning-focused evaluation and model development in a linguistically underrepresented context. Using SOMADHAN, we evaluated a range of large language models (LLMs) - including GPT-4o, GPT-3.5 Turbo, LLaMA series models, Deepseek, and Qwen - through both zero-shot and few-shot prompting with and without Chain of Thought (CoT) reasoning. CoT prompting consistently improved performance over standard prompting, especially in tasks requiring multi-step logic. LLaMA-3.3 70B achieved the highest accuracy of 88% with few-shot CoT prompting. We also applied Low-Rank Adaptation (LoRA) to fine-tune models efficiently, enabling them to adapt to Bengali MWPs with minimal computational cost. Our work fills a critical gap in Bengali NLP by providing a high-quality reasoning dataset and a scalable framework for solving complex MWPs. We aim to advance equitable research in low-resource languages and enhance reasoning capabilities in educational and language technologies.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21354
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging Large Language Models for Bengali Math Word Problem Solving with Chain of Thought Reasoning
Paul, Bidyarthi
Era, Jalisha Jashim
Zim, Mirazur Rahman
Aothoi, Tahmid Sattar
Shah, Faisal Muhammad
Computation and Language
Machine Learning
Solving Bengali Math Word Problems (MWPs) remains a major challenge in natural language processing (NLP) due to the language's low-resource status and the multi-step reasoning required. Existing models struggle with complex Bengali MWPs, largely because no human-annotated Bengali dataset has previously addressed this task. This gap has limited progress in Bengali mathematical reasoning. To address this, we created SOMADHAN, a dataset of 8792 complex Bengali MWPs with manually written, step-by-step solutions. We designed this dataset to support reasoning-focused evaluation and model development in a linguistically underrepresented context. Using SOMADHAN, we evaluated a range of large language models (LLMs) - including GPT-4o, GPT-3.5 Turbo, LLaMA series models, Deepseek, and Qwen - through both zero-shot and few-shot prompting with and without Chain of Thought (CoT) reasoning. CoT prompting consistently improved performance over standard prompting, especially in tasks requiring multi-step logic. LLaMA-3.3 70B achieved the highest accuracy of 88% with few-shot CoT prompting. We also applied Low-Rank Adaptation (LoRA) to fine-tune models efficiently, enabling them to adapt to Bengali MWPs with minimal computational cost. Our work fills a critical gap in Bengali NLP by providing a high-quality reasoning dataset and a scalable framework for solving complex MWPs. We aim to advance equitable research in low-resource languages and enhance reasoning capabilities in educational and language technologies.
title Leveraging Large Language Models for Bengali Math Word Problem Solving with Chain of Thought Reasoning
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2505.21354