Right at My Level: A Unified Multilingual Framework for Proficiency-Aware Text Simplification

TL;DR

This paper introduces Re-RIGHT, a reinforcement learning framework for multilingual text simplification that adapts to proficiency levels without needing parallel corpora, outperforming large language model baselines.

Contribution

It presents a novel reinforcement learning approach that effectively simplifies text across multiple languages and proficiency levels without relying on parallel corpora.

Findings

Re-RIGHT achieves higher lexical coverage at target proficiency levels.

Re-RIGHT maintains semantic integrity and fluency better than LLM baselines.

Collected 43K vocabulary-level data across four languages for training.

Abstract

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.