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

arXiv: https://arxiv.org/abs/2604.05302 · HTML: https://mlsanity.com/paper/2604.05302/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 57 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Sentence Simplification with Deep Reinforcement Learning](https://mlsanity.com/paper/1703.10931/) (2017)
- [LENS: A Learnable Evaluation Metric for Text Simplification](https://mlsanity.com/paper/2212.09739/) (2022)
- [BLESS: Benchmarking Large Language Models on Sentence Simplification](https://mlsanity.com/paper/2310.15773/) (2023)
- [Revisiting non-English Text Simplification: A Unified Multilingual Benchmark](https://mlsanity.com/paper/2305.15678/) (2023)
- [ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment](https://mlsanity.com/paper/2305.14463/) (2023)
- [From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation](https://mlsanity.com/paper/2406.03030/) (2024)
- [Analysing Zero-Shot Readability-Controlled Sentence Simplification](https://mlsanity.com/paper/2409.20246/) (2024)
- [UniversalCEFR: Enabling Open Multilingual Research on Language Proficiency Assessment](https://mlsanity.com/paper/2506.01419/) (2025)
- [Deep Learning Approaches to Lexical Simplification: A Survey](https://mlsanity.com/paper/2305.12000/) (2023)
- [Ace-CEFR -- A Dataset for Automated Evaluation of the Linguistic Difficulty of Conversational Texts for LLM Applications](https://mlsanity.com/paper/2506.14046/) (2025)
- [Aligning Sentence Simplification with ESL Learner's Proficiency for Language Acquisition](https://mlsanity.com/paper/2502.11457/) (2025)
- [Simple is not Enough: Document-level Text Simplification using Readability and Coherence](https://mlsanity.com/paper/2412.18655/) (2024)
- [German4All -- A Dataset and Model for Readability-Controlled Paraphrasing in German](https://mlsanity.com/paper/2508.17973/) (2025)

## Abstract (arXiv)

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.