SimpCue：面向多语言文本简化的基于提示的线索方法
SimpCue: Cue-Based Prompting for Multilingual Text Simplification
浏览论文内容
中文总结 AI 辅助
本研究针对加泰罗尼亚语、西班牙语、意大利语的多语言易读性文本简化任务，以Qwen3-8B为模型，对比不同提示方式的效果，发现预测线索提示表现最优但提升有限。
中文摘要 AI 辅助
文本简化旨在在保留原文含义的同时，让复杂文本更易于理解。近期的大语言模型可通过提示实现简化，但向提示中添加关于句子复杂性的显式语言信息是否能提升输出效果仍不明确。针对加泰罗尼亚语、西班牙语和意大利语的多语言句子级易读性文本简化任务，本研究探讨了该问题。使用Qwen3-8B模型，我们对比了三种提示方式：基线提示、添加了人工标注语言线索的黄金线索提示、添加了自动预测线索的预测线索提示。我们采用SARI、BLEU、chrF和BERTScore指标评估输出，并辅以人工定性分析。预测线索提示在全部四项指标中取得了最佳综合得分，不过相比基线的提升幅度较小；黄金线索提示未始终优于基线，且结果随语言变化而不同。这些发现表明，基于线索的提示可对多语言易读性文本简化产生影响，但其益处有限，且依赖于指标和语言。
英文摘要
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.
发表机构
- Universitat Pompeu Fabra (UPF)（庞培法布拉大学）
机构由 AI 辅助整理，请以论文原文为准。
