通过迭代后编辑提升西班牙语文本可读性，获两项榜首。
Text Adaptation to Plain Language and Easy Read via Automatic Post-Editing Cycles
- 用大模型生成初版，再逐轮自动后编辑优化
- 在可读性和相似度指标稳定后停止迭代
- 适合需要精准易读文本的政策与医疗场景
本文介绍Vicomtech在西班牙语简易阅读与通俗语言转换挑战赛中的参与情况。方法基于对不同初始大模型生成结果的自动后编辑，通过迭代生成多轮适应版本，直至可读性与相似度指标不再显著提升为止。最终提交结果在官方平均评分中，分别获得通俗语言和简易阅读任务的第一名与第二名。
原文摘要 · Abstract (English)
We describe Vicomtech's participation in the CLEARS challenge on text adaptation to Plain Language and Easy Read in Spanish. Our approach features automatic post-editing of different types of initial Large Language Model adaptations, where successive adaptations are generated iteratively until readability and similarity metrics indicate that no further adaptation refinement can be successfully performed. Taking the average of all official metrics, our submissions achieved first and second place in Plain language and Easy Read adaptation, respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。