Redefining Simplicity: Benchmarking Large Language Models from Lexical to Document Simplification
This study addresses the problem of text simplification for natural language processing applications, providing insights for researchers and developers working with large language models.
The study tackled the problem of text simplification across four tasks, and found that large language models outperformed non-LLM methods in all tasks, often generating outputs that exceeded the quality of human-annotated references. The results showed significant improvements in text simplification quality.
Text simplification (TS) refers to the process of reducing the complexity of a text while retaining its original meaning and key information. Existing work only shows that large language models (LLMs) have outperformed supervised non-LLM-based methods on sentence simplification. This study offers the first comprehensive analysis of LLM performance across four TS tasks: lexical, syntactic, sentence, and document simplification. We compare lightweight, closed-source and open-source LLMs against traditional non-LLM methods using automatic metrics and human evaluations. Our experiments reveal that LLMs not only outperform non-LLM approaches in all four tasks but also often generate outputs that exceed the quality of existing human-annotated references. Finally, we present some future directions of TS in the era of LLMs.