# Simplicity Level Estimate (SLE): A Learned Reference-Less Metric for Sentence Simplification

arXiv: https://arxiv.org/abs/2310.08170 · HTML: https://mlsanity.com/paper/2310.08170/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 12 Oct 2023.

## Builds on (most cited first, 12 of 12)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [QuestEval: Summarization Asks for Fact-based Evaluation](https://mlsanity.com/paper/2103.12693/) (2021)
- [Controllable Sentence Simplification](https://mlsanity.com/paper/1910.02677/) (2019)
- [LENS: A Learnable Evaluation Metric for Text Simplification](https://mlsanity.com/paper/2212.09739/) (2022)
- [Semantic Structural Evaluation for Text Simplification](https://mlsanity.com/paper/1810.05022/) (2018)
- [Document-Level Text Simplification: Dataset, Criteria and Baseline](https://mlsanity.com/paper/2110.05071/) (2021)
- [On the Ethical Considerations of Text Simplification](https://mlsanity.com/paper/2204.09565/) (2022)
- [Rethinking Automatic Evaluation in Sentence Simplification](https://mlsanity.com/paper/2104.07560/) (2021)
- [A Neural Pairwise Ranking Model for Readability Assessment](https://mlsanity.com/paper/2203.07450/) (2022)
- [Reference-less Quality Estimation of Text Simplification Systems](https://mlsanity.com/paper/1901.10746/) (2019)
- [A Sentence Simplification System for Improving Relation Extraction](https://mlsanity.com/paper/1703.09013/) (2017)
- [Context-Aware Document Simplification](https://mlsanity.com/paper/2305.06274/) (2023)

## Built on by (most cited first, 14 of 14)

- [Improving Minimum Bayes Risk Decoding with Multi-Prompt](https://mlsanity.com/paper/2407.15343/) (2024)
- [Evaluating Document Simplification: On the Importance of Separately Assessing Simplicity and Meaning Preservation](https://mlsanity.com/paper/2404.03278/) (2024)
- [Evaluation Under Imperfect Benchmarks and Ratings: A Case Study in Text Simplification](https://mlsanity.com/paper/2504.09394/) (2025)
- [REFeREE: A REference-FREE Model-Based Metric for Text Simplification](https://mlsanity.com/paper/2403.17640/) (2024)
- [Label Confidence Weighted Learning for Target-level Sentence Simplification](https://mlsanity.com/paper/2410.05748/) (2024)
- [ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Sentence](https://mlsanity.com/paper/2411.05172/) (2024)
- [SiTSE: Sinhala Text Simplification Dataset and Evaluation](https://mlsanity.com/paper/2412.01293/) (2024)
- [Aligning Sentence Simplification with ESL Learner's Proficiency for Language Acquisition](https://mlsanity.com/paper/2502.11457/) (2025)
- [Readability-guided Idiom-aware Sentence Simplification (RISS) for Chinese](https://mlsanity.com/paper/2406.02974/) (2024)
- [XPlainVerse: A Million-Scale Benchmark for Explainable Deepfake Detection](https://mlsanity.com/paper/2607.03562/) (2026)
- [Evaluating the Effectiveness of Direct Preference Optimization for Personalizing German Automatic Text Simplifications for Persons with Intellectual Disabilities](https://mlsanity.com/paper/2507.01479/) (2025)
- [Text Adaptation to Plain Language and Easy Read via Automatic Post-Editing Cycles](https://mlsanity.com/paper/2509.11991/) (2025)
- [Four Quadrants of Difficulty: A Simple Categorisation and its Limits](https://mlsanity.com/paper/2601.01488/) (2026)
- [Improving Health Literacy through Lay Summarization of Radiological Reports: An Evaluation of BioNER and Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.02396/) (2026)

## Abstract (arXiv)

Automatic evaluation for sentence simplification remains a challenging problem. Most popular evaluation metrics require multiple high-quality references -- something not readily available for simplification -- which makes it difficult to test performance on unseen domains. Furthermore, most existing metrics conflate simplicity with correlated attributes such as fluency or meaning preservation. We propose a new learned evaluation metric (SLE) which focuses on simplicity, outperforming almost all existing metrics in terms of correlation with human judgements.