Difficulty Estimation and Simplification of French Text Using LLMs

TL;DR

This paper presents a method using large language models to estimate difficulty and simplify French texts for language learning, achieving high accuracy and effective simplification with limited fine-tuning.

Contribution

It introduces a novel approach leveraging transfer learning and LLMs for difficulty estimation and text simplification, demonstrating superior accuracy and language-agnostic applicability.

Findings

Superior difficulty classification accuracy compared to previous methods

Effective text simplification with limited fine-tuning

Methods applicable to multiple languages

Abstract

We leverage generative large language models for language learning applications, focusing on estimating the difficulty of foreign language texts and simplifying them to lower difficulty levels. We frame both tasks as prediction problems and develop a difficulty classification model using labeled examples, transfer learning, and large language models, demonstrating superior accuracy compared to previous approaches. For simplification, we evaluate the trade-off between simplification quality and meaning preservation, comparing zero-shot and fine-tuned performances of large language models. We show that meaningful text simplifications can be obtained with limited fine-tuning. Our experiments are conducted on French texts, but our methods are language-agnostic and directly applicable to other foreign languages.