End-to-End Bangla AI for Solving Math Olympiad Problem Benchmark: Leveraging Large Language Model Using Integrated Approach

TL;DR

This paper presents an integrated approach to improve large language models for solving Bangla math Olympiad problems by combining fine-tuning, retrieval-augmented generation, and iterative reasoning to enhance accuracy and reasoning skills.

Contribution

It introduces a systematic method for enhancing LLMs' mathematical reasoning in Bangla through dataset augmentation, customized prompting, and RAG techniques.

Findings

Enhanced reasoning accuracy in Bangla math problems

Improved model efficiency with dataset augmentation

Iterative reasoning boosts problem-solving performance

Abstract

This work introduces systematic approach for enhancing large language models (LLMs) to address Bangla AI mathematical challenges. Through the assessment of diverse LLM configurations, fine-tuning with specific datasets, and the implementation of Retrieval-Augmented Generation (RAG), we enhanced the model's reasoning precision in a multilingual setting. Crucial discoveries indicate that customized prompting, dataset augmentation, and iterative reasoning improve the model's efficiency regarding Olympiad-level mathematical challenges.