Translate or Simplify First: An Analysis of Cross-lingual Text Simplification in English and French

2026-04-26

AI Summary

This study addresses the challenge of cross-lingual text simplification, which requires joint handling of translation and simplification, yet the optimal sequencing of these operations remains unclear. The authors systematically evaluate five large language model prompting strategies—direct joint processing, translate-then-simplify, simplify-then-translate, and two decomposed pipelines—on bidirectional English–French tasks across multiple genres. Employing a multidimensional evaluation framework that integrates automatic metrics, linguistic features, and human assessments across seven state-of-the-art large language models, the work reveals that direct prompting achieves the highest BLEU scores (indicating superior semantic fidelity), whereas the translate-then-simplify approach yields the greatest simplification. These findings underscore the critical influence of operational order on the trade-off between simplicity and semantic preservation in cross-lingual simplification outputs.

Technology Category

• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Cross-Lingual Text Simplification (CLTS) aims to make content more accessible across languages by simultaneously addressing both linguistic complexity and translation. This study investigates the effectiveness of different prompting strategies for CLTS between English and French using large language models (LLMs). We examine five distinct prompting systems: a direct prompt instructing the LLM to perform both translation and simplification simultaneously, two Composition approaches that either translate-then-simplify or simplify-then-translate within a single prompt, and two decomposition approaches that perform the same operations in separate, consecutive prompts. These systems are evaluated across a diverse set of five corpora of different genres (Wikipedia and medical texts) using seven state-of-the-art LLMs. Output quality is assessed through a multi-faceted evaluation framework comprising automatic metrics, comprehensive linguistic feature analysis, and human evaluation of simplicity and meaning preservation. Our findings reveal that while direct prompting consistently achieves the highest BLEU scores, indicating meaning fidelity, Translate-then-Simplify approaches demonstrate the highest simplicity, as measured by the linguistic features.

Problem

• Cross-Lingual Text Simplification
• Translation
• Text Simplification
• Large Language Models
• Multilingual Accessibility

Innovation

• Cross-Lingual Text Simplification
• Prompting Strategies
• Large Language Models
• Simplification-Translation Trade-off
• Multidimensional Evaluation