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

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.

References in corpus (11)

• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• Qwen2.5 Technical Report
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis
• MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
• ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
• Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B
• MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models Using Odyssey Math Data
• Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
• BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search