# Generating Summaries with Controllable Readability Levels

arXiv: https://arxiv.org/abs/2310.10623 · HTML: https://mlsanity.com/paper/2310.10623/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 90 references that are in the map.
- First posted on arXiv 16 Oct 2023.

## Builds on (most cited first, 30 of 47)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://mlsanity.com/paper/2210.07197/) (2022)
- [Style Transfer from Non-Parallel Text by Cross-Alignment](https://mlsanity.com/paper/1705.09655/) (2017)
- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [Controllable Abstractive Summarization](https://mlsanity.com/paper/1711.05217/) (2017)
- [CTRLsum: Towards Generic Controllable Text Summarization](https://mlsanity.com/paper/2012.04281/) (2020)
- [Best-Worst Scaling More Reliable than Rating Scales: A Case Study on Sentiment Intensity Annotation](https://mlsanity.com/paper/1712.01765/) (2017)
- [Controllable Sentence Simplification](https://mlsanity.com/paper/1910.02677/) (2019)
- [Better Rewards Yield Better Summaries: Learning to Summarise Without References](https://mlsanity.com/paper/1909.01214/) (2019)
- [Gradient-Based Constrained Sampling from Language Models](https://mlsanity.com/paper/2205.12558/) (2022)
- [Felix: Flexible Text Editing Through Tagging and Insertion](https://mlsanity.com/paper/2003.10687/) (2020)
- [Making Science Simple: Corpora for the Lay Summarisation of Scientific Literature](https://mlsanity.com/paper/2210.09932/) (2022)
- [Controllable Text Simplification with Explicit Paraphrasing](https://mlsanity.com/paper/2010.11004/) (2020)
- [Paragraph-level Simplification of Medical Texts](https://mlsanity.com/paper/2104.05767/) (2021)
- [Faithful or Extractive? On Mitigating the Faithfulness-Abstractiveness Trade-off in Abstractive Summarization](https://mlsanity.com/paper/2108.13684/) (2021)
- [ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfer](https://mlsanity.com/paper/2306.07799/) (2023)
- [Supervised and Unsupervised Neural Approaches to Text Readability](https://mlsanity.com/paper/1907.11779/) (2019)
- [Automated Lay Language Summarization of Biomedical Scientific Reviews](https://mlsanity.com/paper/2012.12573/) (2020)
- [Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen](https://mlsanity.com/paper/2005.00701/) (2020)
- [Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text](https://mlsanity.com/paper/2107.03444/) (2021)
- [Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering](https://mlsanity.com/paper/2210.03078/) (2022)

## Built on by (most cited first, 24 of 24)

- [Break the Sequential Dependency of LLM Inference Using Lookahead Decoding](https://mlsanity.com/paper/2402.02057/) (2024)
- [Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization](https://mlsanity.com/paper/2311.09184/) (2023)
- [RAG-RLRC-LaySum at BioLaySumm: Integrating Retrieval-Augmented Generation and Readability Control for Layman Summarization of Biomedical Texts](https://mlsanity.com/paper/2405.13179/) (2024)
- [Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Survey](https://mlsanity.com/paper/2311.09212/) (2023)
- [From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation](https://mlsanity.com/paper/2406.03030/) (2024)
- [Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic](https://mlsanity.com/paper/2402.14798/) (2024)
- [Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards](https://mlsanity.com/paper/2409.17472/) (2024)
- [RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework](https://mlsanity.com/paper/2410.19109/) (2024)
- [ReadCtrl: Personalizing text generation with readability-controlled instruction learning](https://mlsanity.com/paper/2406.09205/) (2024)
- [Measuring and Modifying the Readability of English Texts with GPT-4](https://mlsanity.com/paper/2410.14028/) (2024)
- [Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMs](https://mlsanity.com/paper/2406.04460/) (2024)
- [Speechworthy Instruction-tuned Language Models](https://mlsanity.com/paper/2409.14672/) (2024)
- [Free-text Rationale Generation under Readability Level Control](https://mlsanity.com/paper/2407.01384/) (2024)
- [MODS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries in Document Collections](https://mlsanity.com/paper/2502.00322/) (2025)
- [Multi-Facet Blending for Faceted Query-by-Example Retrieval](https://mlsanity.com/paper/2412.01443/) (2024)
- [Beyond One-Size-Fits-All Summarization: Customizing Summaries for Diverse Users](https://mlsanity.com/paper/2503.10675/) (2025)
- [RephQA: Evaluating Readability of Large Language Models in Public Health Question Answering](https://mlsanity.com/paper/2509.16360/) (2025)
- [Classroom AI: Large Language Models as Grade-Specific Teachers](https://mlsanity.com/paper/2601.06225/) (2026)
- [Exploring Iterative Controllable Summarization with Large Language Models](https://mlsanity.com/paper/2411.12460/) (2024)
- [Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents](https://mlsanity.com/paper/2509.10935/) (2025)
- [Unsupervised Text Style Transfer for Controllable Intensity](https://mlsanity.com/paper/2601.01060/) (2026)
- [PG-CE: A Progressive Generation Dataset with Constraint Enhancement for Controllable Text Generation](https://mlsanity.com/paper/2509.17669/) (2025)
- [Iterative Prompt Refinement for Dyslexia-Friendly Text Summarization Using GPT-4o](https://mlsanity.com/paper/2602.22524/) (2026)
- [Can LLMs Control Readability? A Multi-Dimensional Evaluation Framework for CEFR-Controlled Arabic Generation](https://mlsanity.com/paper/2606.21981/) (2026)

## Abstract (arXiv)

Readability refers to how easily a reader can understand a written text. Several factors affect the readability level, such as the complexity of the text, its subject matter, and the reader's background knowledge. Generating summaries based on different readability levels is critical for enabling knowledge consumption by diverse audiences. However, current text generation approaches lack refined control, resulting in texts that are not customized to readers' proficiency levels. In this work, we bridge this gap and study techniques to generate summaries at specified readability levels. Unlike previous methods that focus on a specific readability level (e.g., lay summarization), we generate summaries with fine-grained control over their readability. We develop three text generation techniques for controlling readability: (1) instruction-based readability control, (2) reinforcement learning to minimize the gap between requested and observed readability and (3) a decoding approach that uses lookahead to estimate the readability of upcoming decoding steps. We show that our generation methods significantly improve readability control on news summarization (CNN/DM dataset), as measured by various readability metrics and human judgement, establishing strong baselines for controllable readability in summarization.