# Let's Simplify Step by Step: Guiding LLM Towards Multilingual Unsupervised Proficiency-Controlled Sentence Simplification

arXiv: https://arxiv.org/abs/2602.07499 · HTML: https://mlsanity.com/paper/2602.07499/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 47 references that are in the map.
- First posted on arXiv 7 Feb 2026.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Data-to-Text Generation with Content Selection and Planning](https://mlsanity.com/paper/1809.00582/) (2018)
- [Neural CRF Model for Sentence Alignment in Text Simplification](https://mlsanity.com/paper/2005.02324/) (2020)
- [Controllable Sentence Simplification](https://mlsanity.com/paper/1910.02677/) (2019)
- [Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation](https://mlsanity.com/paper/1904.03396/) (2019)
- [EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing](https://mlsanity.com/paper/1906.08104/) (2019)
- [Controllable Text Simplification with Explicit Paraphrasing](https://mlsanity.com/paper/2010.11004/) (2020)
- [Supervised and Unsupervised Neural Approaches to Text Readability](https://mlsanity.com/paper/1907.11779/) (2019)
- [CEFR-Based Sentence Difficulty Annotation and Assessment](https://mlsanity.com/paper/2210.11766/) (2022)
- [Revisiting non-English Text Simplification: A Unified Multilingual Benchmark](https://mlsanity.com/paper/2305.15678/) (2023)
- [Discourse Level Factors for Sentence Deletion in Text Simplification](https://mlsanity.com/paper/1911.10384/) (2019)
- [ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment](https://mlsanity.com/paper/2305.14463/) (2023)
- [Flesch or Fumble? Evaluating Readability Standard Alignment of Instruction-Tuned Language Models](https://mlsanity.com/paper/2309.05454/) (2023)
- [From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation](https://mlsanity.com/paper/2406.03030/) (2024)
- [Controlling Pre-trained Language Models for Grade-Specific Text Simplification](https://mlsanity.com/paper/2305.14993/) (2023)
- [Analysing Zero-Shot Readability-Controlled Sentence Simplification](https://mlsanity.com/paper/2409.20246/) (2024)
- [Controlled Language Generation for Language Learning Items](https://mlsanity.com/paper/2211.15731/) (2022)
- [Simplifying Translations for Children: Iterative Simplification Considering Age of Acquisition with LLMs](https://mlsanity.com/paper/2408.04217/) (2024)

## Built on by (most cited first, 1 of 1)

- [Reinforcement Learning for improving Large Language Models' Catalan text simplification capabilities](https://mlsanity.com/paper/2609.04823/) (2026)

## Abstract (arXiv)

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.