就在我的水平上：一种统一的多语言框架，用于面向能力的文本简化
Right at My Level: A Unified Multilingual Framework for Proficiency-Aware Text Simplification
AI总结：
本文提出Re-RIGHT框架，通过强化学习实现无需平行语料的多语言文本简化，提升目标水平的词汇覆盖和语义保持。
摘要：
文本简化通过提供易懂输入支持二语学习，符合输入假说。然而，构建个性化平行语料库成本高，现有基于大语言模型的可读性控制方法依赖预标记句子语料，主要针对英语。我们提出Re-RIGHT，一种统一的强化学习框架，用于自适应多语言文本简化，无需平行语料监督。我们首先表明，基于提示的词汇简化在目标水平（CEFR、JLPT、TOPIK和HSK）表现不佳，即使使用GPT-5.2和Gemini 2.5等先进LLM。为解决此问题，我们收集了43K词汇级数据，涵盖四种语言（英语、日语、韩语和中文），并训练了一个紧凑的4B策略模型，集成了三个奖励模块：词汇覆盖、语义保持和连贯性。与更强的LLM基线相比，Re-RIGHT在目标水平实现了更高的词汇覆盖，同时保持原始意义和流畅性。
英文摘要：
Text simplification supports second language (L2) learning by providing comprehensible input, consistent with the Input Hypothesis. However, constructing personalized parallel corpora is costly, while existing large language model (LLM)-based readability control methods rely on pre-labeled sentence corpora and primarily target English. We propose Re-RIGHT, a unified reinforcement learning framework for adaptive multilingual text simplification without parallel corpus supervision. We first show that prompting-based lexical simplification at target proficiency levels (CEFR, JLPT, TOPIK, and HSK) performs poorly at easier levels and for non-English languages, even with state-of-the-art LLMs such as GPT-5.2 and Gemini 2.5. To address this, we collect 43K vocabulary-level data across four languages (English, Japanese, Korean, and Chinese) and train a compact 4B policy model using Re-RIGHT, which integrates three reward modules: vocabulary coverage, semantic preservation, and coherence. Compared to the stronger LLM baselines, Re-RIGHT achieves higher lexical coverage at target proficiency levels while maintaining original meaning and fluency.
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。
