SimpCue: Cue-Based Prompting for Multilingual Text Simplification
Computation and LanguageArtificial Intelligence
Summary
The authors studied how adding hints about sentence complexity affects a large language model's ability to simplify sentences in Catalan, Spanish, and Italian. They tested three types of prompts: a basic one, one with perfect (gold) complexity hints, and one with automatically predicted hints. Their results show that using predicted hints helps the model a little, but the improvement is small and changes depending on the language and evaluation metric. Using perfect hints didn’t consistently make the outputs better. Overall, the authors found that adding complexity cues influences simplification but only modestly.
Text simplificationLarge language modelsPromptingSentence complexityMultilingual NLPEasy-to-ReadQwen3-8BSARIBLEUBERTScore
Authors
Mehrzad Tareh, Horacio Saggion, Stefan Bott
Abstract
Text simplification aims to make complex texts easier to understand while preserving their original meaning. Recent large language models can perform simplification through prompting, but it remains unclear whether adding explicit linguistic information about sentence complexity to the prompt improves their outputs. We investigate this question for multilingual sentence-level Easy-to-Read simplification in Catalan, Spanish, and Italian. Using Qwen3-8B, we compare a baseline prompt, a gold-cue prompt enriched with gold linguistic cues, and a predicted-cue prompt enriched with automatically predicted cues. We evaluate the outputs using SARI, BLEU, chrF, and BERTScore, and complement this evaluation with a manual qualitative analysis. Predicted-cue prompting obtains the best overall scores across all four metrics, although the gains over the baseline are small. Gold-cue prompting does not consistently improve over the baseline, and results vary across languages. These findings indicate that cue-based prompting can influence multilingual Easy-to-Read simplification, but its benefits are modest, metric-dependent, and language-dependent.