逐步简化：引导LLM实现多语言无监督能力控制的句子简化
Let's Simplify Step by Step: Guiding LLM Towards Multilingual Unsupervised Proficiency-Controlled Sentence Simplification
AI总结：
本文提出一种多语言无监督句子简化框架，通过分步骤简化提升控制能力，但发现保持语义忠实仍具挑战性。
摘要：
大型语言模型在能力控制的句子简化任务中表现出有限的能力，特别是在处理大可读性水平时。我们提出了一种框架，通过动态路径规划、语义感知的示例选择以及结合对话历史的思维链生成，将复杂的简化分解为可管理的步骤。在两个基准测试中对五种语言的评估显示，我们的方法在提高简化效果的同时，将计算步骤减少了22-42%。人类评估证实了简化效果与意义保持之间的基本权衡。值得注意的是，即使人类标注者也难以就语义保持的判断达成一致，突显了这项任务的固有复杂性。我们的工作表明，虽然逐步简化提高了控制能力，但在广泛简化过程中保持语义忠实仍然是一个开放性挑战。
英文摘要：
Large language models demonstrate limited capability in proficiency-controlled sentence simplification, particularly when simplifying across large readability levels. We propose a framework that decomposes complex simplifications into manageable steps through dynamic path planning, semantic-aware exemplar selection, and chain-of-thought generation with conversation history for coherent reasoning. Evaluation on five languages across two benchmarks shows our approach improves simplification effectiveness while reducing computational steps by 22-42%. Human evaluation confirms the fundamental trade-off between simplification effectiveness and meaning preservation. Notably, even human annotators struggle to agree on semantic preservation judgments, highlighting the inherent complexity of this task. Our work shows that while step-by-step simplification improves control, preserving semantic fidelity during extensive simplification remains an open challenge.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
