Sentence Simplification via Large Language Models

TL;DR

This paper evaluates large language models for sentence simplification, demonstrating they outperform existing methods and match human performance in quality, using zero- and few-shot learning on benchmark datasets.

Contribution

It provides an empirical analysis of LLMs' effectiveness in sentence simplification, highlighting their potential as high-quality systems without extensive training.

Findings

LLMs outperform state-of-the-art methods

LLMs are comparable to human annotators

Zero-/few-shot learning is effective for simplification

Abstract

Sentence Simplification aims to rephrase complex sentences into simpler sentences while retaining original meaning. Large Language models (LLMs) have demonstrated the ability to perform a variety of natural language processing tasks. However, it is not yet known whether LLMs can be served as a high-quality sentence simplification system. In this work, we empirically analyze the zero-/few-shot learning ability of LLMs by evaluating them on a number of benchmark test sets. Experimental results show LLMs outperform state-of-the-art sentence simplification methods, and are judged to be on a par with human annotators.