mlsanityData to 14 Oct 2026

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

arXiv 2604.23844 ↗First posted 26 Apr 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 43 references that are in the map. First posted on arXiv 26 Apr 2026.

Builds on

18 of 43 references.

References · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  6. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
  7. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 593
  8. 2019CamemBERT: a Tasty French Language Modelcited by 368
  9. 2024Aya Model: An Instruction Finetuned Open-Access Multilingual Language Modelcited by 295
  10. 2017Sentence Simplification with Deep Reinforcement Learningcited by 109
  11. 2020Neural CRF Model for Sentence Alignment in Text Simplificationcited by 106
  12. 2020ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformationscited by 101
6 more
  1. 2018BLEU is Not Suitable for the Evaluation of Text Simplificationcited by 78
  2. 2019EASSE: Easier Automatic Sentence Simplification Evaluationcited by 50
  3. 2023Revisiting non-English Text Simplification: A Unified Multilingual Benchmarkcited by 27
  4. 2023Towards Explainable Evaluation Metrics for Machine Translationcited by 15
  5. 2016Readability-based Sentence Ranking for Evaluating Text Simplificationcited by 5
  6. 2022(Psycho-)Linguistic Features Meet Transformer Models for Improved Explainable and Controllable Text Simplificationcited by 4

Built on by

Not cited yet.