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

• URL: http://arxiv.org/abs/2505.21354v2
• Date: Wed, 30 Jul 2025 03:20:16 GMT
• Title: Leveraging Large Language Models for Bengali Math Word Problem Solving with Chain of Thought Reasoning
• Authors: Bidyarthi Paul, Jalisha Jashim Era, Mirazur Rahman Zim, Tahmid Sattar Aothoi, Faisal Muhammad Shah,
• Abstract summary: Solving Bengali Math Word Problems (MWPs) remains a major challenge in natural language processing (NLP)<n>No human-annotated Bengali dataset has previously addressed this task.<n>We created SOMADHAN, a dataset of 8792 complex Bengali MWPs with manually written, step-by-step solutions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• HeQ: a Large and Diverse Hebrew Reading Comprehension Benchmark [54.73504952691398]
  We set out to deliver a Hebrew Machine Reading dataset as extractive Questioning.<n>The morphologically rich nature of Hebrew poses a challenge to this endeavor.<n>We devise a novel set of guidelines, a controlled crowdsourcing protocol, and revised evaluation metrics.
  arXiv  Detail & Related papers  (2025-08-03T15:53:01Z)
• Evaluating LLMs' Multilingual Capabilities for Bengali: Benchmark Creation and Performance Analysis [0.0]
  Bengali is an underrepresented language in NLP research.<n>We systematically investigate the challenges that hinder Bengali NLP performance.<n>Our findings reveal consistent performance gaps for Bengali compared to English.
  arXiv  Detail & Related papers  (2025-07-31T05:16:43Z)
• BnMMLU: Measuring Massive Multitask Language Understanding in Bengali [0.0]
  We introduce BnMMLU, a benchmark to evaluate the language understanding capabilities of Bengali in language models.<n>The dataset spans 23 domains, including science, humanities, mathematics and general knowledge.<n>We benchmark several proprietary and open-source large language models (LLMs) on the BnMMLU test set.
  arXiv  Detail & Related papers  (2025-05-25T02:54:31Z)
• Demystifying Multilingual Chain-of-Thought in Process Reward Modeling [71.12193680015622]
  We tackle the challenge of extending process reward models (PRMs) to multilingual settings.<n>We train multilingual PRMs on a dataset spanning seven languages, which is translated from English.<n>Our results highlight the sensitivity of multilingual PRMs to both the number of training languages and the volume of English data.
  arXiv  Detail & Related papers  (2025-02-18T09:11:44Z)
• Empowering Bengali Education with AI: Solving Bengali Math Word Problems through Transformer Models [0.0]
  This paper develops an innovative approach to solving Bengali MWPs using transformer-based models.<n>To support this effort, the "PatiGonit" dataset was introduced, containing 10,000 Bengali math problems.<n>The evaluation revealed that the mT5 model achieved the highest accuracy of 97.30%.
  arXiv  Detail & Related papers  (2025-01-05T16:50:55Z)
• Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMs [2.309018557701645]
  We aim to explore the question of whether there is a need for English-oriented Large Language Models dedicated to a low-resource language.<n>We compare the performance of open-weight and closed-source LLMs against fine-tuned encoder-decoder models.<n>Our findings reveal that while LLMs generally excel in reasoning tasks, their performance in tasks requiring Bengali script generation is inconsistent.
  arXiv  Detail & Related papers  (2024-06-29T11:50:16Z)
• The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights [108.40766216456413]
  We propose a question alignment framework to bridge the gap between large language models' English and non-English performance. Experiment results show it can boost multilingual performance across diverse reasoning scenarios, model families, and sizes. We analyze representation space, generated response and data scales, and reveal how question translation training strengthens language alignment within LLMs.
  arXiv  Detail & Related papers  (2024-05-02T14:49:50Z)
• Simultaneous Machine Translation with Large Language Models [51.470478122113356]
  We investigate the possibility of applying Large Language Models to SimulMT tasks. We conducted experiments using the textttLlama2-7b-chat model on nine different languages from the MUST-C dataset. The results show that LLM outperforms dedicated MT models in terms of BLEU and LAAL metrics.
  arXiv  Detail & Related papers  (2023-09-13T04:06:47Z)
• PAL: Program-aided Language Models [112.94785609781503]
  We present Program-Aided Language models (PaL) to understand natural language problems. PaL offloads the solution step to a programmatic runtime such as a Python interpreter. We set new state-of-the-art results in all 12 benchmarks.
  arXiv  Detail & Related papers  (2022-11-18T18:56:13Z)
• Chain of Thought Prompting Elicits Reasoning in Large Language Models [56.811278668446825]
  This paper explores the ability of language models to generate a coherent chain of thought. Experiments show that inducing a chain of thought via prompting can enable sufficiently large language models to better perform reasoning tasks.
  arXiv  Detail & Related papers  (2022-01-28T02:33:07Z)
• Generate & Rank: A Multi-task Framework for Math Word Problems [48.99880318686938]
  Math word problem (MWP) is a challenging and critical task in natural language processing. We propose Generate & Rank, a framework based on a generative pre-trained language model. By joint training with generation and ranking, the model learns from its own mistakes and is able to distinguish between correct and incorrect expressions.
  arXiv  Detail & Related papers  (2021-09-07T12:21:49Z)
• A Continuous Space Neural Language Model for Bengali Language [0.4799822253865053]
  This paper proposes a continuous-space neural language model, or more specifically an ASGD weight dropped LSTM language model, along with techniques to efficiently train it for Bengali Language. The proposed architecture outperforms its counterparts by achieving an inference perplexity as low as 51.2 on the held out data set for Bengali.
  arXiv  Detail & Related papers  (2020-01-11T14:50:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.