A Hybrid Multi-Agent Prompting Approach for Simplifying Complex Sentences

TL;DR

This paper introduces a hybrid multi-agent prompting method using large language models to effectively simplify complex sentences, significantly outperforming single-agent approaches in accuracy.

Contribution

The paper presents a novel hybrid multi-agent prompting approach that improves sentence simplification performance over existing single-agent methods.

Findings

Successfully simplified 70% of complex sentences in a video game design context.

Outperformed single-agent approaches, which achieved 48% success.

Demonstrated the effectiveness of multi-agent architectures in sentence simplification.

Abstract

This paper addresses the challenge of transforming complex sentences into sequences of logical, simplified sentences while preserving semantic and logical integrity with the help of Large Language Models. We propose a hybrid approach that combines advanced prompting with multi-agent architectures to enhance the sentence simplification process. Experimental results show that our approach was able to successfully simplify 70% of the complex sentences written for video game design application. In comparison, a single-agent approach attained a 48% success rate on the same task.