Solving the multiplication problem of a large language model system using a graph-based method

TL;DR

This paper introduces a graph-based multiplication algorithm that significantly improves the accuracy of large number multiplication in GPT-based models, achieving perfect results on extensive tests by mimicking human-like numerical operations.

Contribution

The paper presents a novel graph-based multiplication method that enhances large number multiplication accuracy in language models, bridging the gap between human intuition and AI algorithms.

Findings

Achieved 100% accuracy on 1,000,000 large number multiplications.

Effectively solved multiplication challenges in GPT-based and other large language models.

Demonstrated the importance of human-inspired insights in AI algorithm design.

Abstract

The generative pre-trained transformer (GPT)-based chatbot software ChatGPT possesses excellent natural language processing capabilities but is inadequate for solving arithmetic problems, especially multiplication. Its GPT structure uses a computational graph for multiplication, which has limited accuracy beyond simple multiplication operations. We developed a graph-based multiplication algorithm that emulated human-like numerical operations by incorporating a 10k operator, where k represents the maximum power to base 10 of the larger of two input numbers. Our proposed algorithm attained 100% accuracy for 1,000,000 large number multiplication tasks, effectively solving the multiplication challenge of GPT-based and other large language models. Our work highlights the importance of blending simple human insights into the design of artificial intelligence algorithms. Keywords: Graph-based multiplication; ChatGPT; Multiplication problem