Right at My Level: A Unified Multilingual Framework for Proficiency-Aware Text Simplification
This addresses the need for adaptive multilingual text simplification for second language learners without requiring parallel corpus supervision, though it is incremental as it builds on existing reinforcement learning and reward-based methods.
The paper tackled the problem of costly personalized parallel corpora and poor performance of LLM-based methods for multilingual text simplification at easier proficiency levels by proposing Re-RIGHT, a reinforcement learning framework that achieved higher lexical coverage at target proficiency levels while maintaining meaning and fluency compared to strong LLM baselines.
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.