# Zero-shot Large Language Models for Automatic Readability Assessment

arXiv: https://arxiv.org/abs/2604.24470 · HTML: https://mlsanity.com/paper/2604.24470/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 62 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic](https://mlsanity.com/paper/2101.01785/) (2020)
- [Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier](https://mlsanity.com/paper/2412.04261/) (2024)
- [Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages](https://mlsanity.com/paper/2212.05409/) (2022)
- [ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations](https://mlsanity.com/paper/2005.00481/) (2020)
- [Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models](https://mlsanity.com/paper/2302.13439/) (2023)
- [Text Readability Assessment for Second Language Learners](https://mlsanity.com/paper/1906.07580/) (2019)
- [Supervised and Unsupervised Neural Approaches to Text Readability](https://mlsanity.com/paper/1907.11779/) (2019)
- [GREEK-BERT: The Greeks visiting Sesame Street](https://mlsanity.com/paper/2008.12014/) (2020)
- [Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features](https://mlsanity.com/paper/2109.12258/) (2021)
- [Linguistic Features for Readability Assessment](https://mlsanity.com/paper/2006.00377/) (2020)
- [BERT Embeddings for Automatic Readability Assessment](https://mlsanity.com/paper/2106.07935/) (2021)
- [ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment](https://mlsanity.com/paper/2305.14463/) (2023)
- [Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations](https://mlsanity.com/paper/2508.03550/) (2025)
- [CamemBERT 2.0: A Smarter French Language Model Aged to Perfection](https://mlsanity.com/paper/2411.08868/) (2024)
- [RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs](https://mlsanity.com/paper/2409.04421/) (2024)
- [Measuring and Modifying the Readability of English Texts with GPT-4](https://mlsanity.com/paper/2410.14028/) (2024)
- [A Unified Neural Network Model for Readability Assessment with Feature Projection and Length-Balanced Loss](https://mlsanity.com/paper/2210.10305/) (2022)
- [MedReadMe: A Systematic Study for Fine-grained Sentence Readability in Medical Domain](https://mlsanity.com/paper/2405.02144/) (2024)
- [Examining Linguistic Shifts in Academic Writing Before and After the Launch of ChatGPT: A Study on Preprint Papers](https://mlsanity.com/paper/2505.12218/) (2025)

## Built on by (most cited first, 3 of 3)

- [TA-RAG: Tone-Aware Retrieval-Augmented Generation for Peer-Support Health Communication](https://mlsanity.com/paper/2606.06794/) (2026)
- [TA-RAG: Tone Awareness as a Design Imperative for Retrieval-Augmented Generation](https://mlsanity.com/paper/2608.06672/) (2026)
- [Assessing Readability with LLMs: The Role of Reasoning and Few-Shot Prompting](https://mlsanity.com/paper/2609.24650/) (2026)

## Abstract (arXiv)

Unsupervised automatic readability assessment (ARA) methods have important practical and research applications (e.g., ensuring medical or educational materials are suitable for their target audiences). In this paper, we propose a new zero-shot prompting methodology for ARA and present the first comprehensive evaluation of using large language models (LLMs) as an unsupervised ARA method by testing 10 diverse open-source LLMs (e.g., different sizes and developers) on 14 diverse datasets (e.g., different text lengths and languages). Our findings show that our proposed prompting methodology outperforms prior methods on 13 of the 14 datasets. Furthermore, we propose LAURAE, which combines LLM and readability formula scores to improve robustness by capturing both contextual and shallow (e.g., sentence length) features of readability. Our evaluation demonstrates that LAURAE robustly outperforms prior methods across languages, text lengths, and amounts of technical language.