# Flesch-Kincaid Readability Depends Only on the Topic Distribution in Long Texts under Topic Models

arXiv: https://arxiv.org/abs/2608.23327 · HTML: https://mlsanity.com/paper/2608.23327/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 47 references that are in the map.
- First posted on arXiv 24 Aug 2026.

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

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Topic Modeling in Embedding Spaces](https://mlsanity.com/paper/1907.04907/) (2019)
- [Autoencoding Variational Inference For Topic Models](https://mlsanity.com/paper/1703.01488/) (2017)
- [Neural Variational Inference for Text Processing](https://mlsanity.com/paper/1511.06038/) (2015)
- [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)
- [Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features](https://mlsanity.com/paper/2109.12258/) (2021)
- [BLESS: Benchmarking Large Language Models on Sentence Simplification](https://mlsanity.com/paper/2310.15773/) (2023)
- [Trends, Limitations and Open Challenges in Automatic Readability Assessment Research](https://mlsanity.com/paper/2105.00973/) (2021)
- [Flesch or Fumble? Evaluating Readability Standard Alignment of Instruction-Tuned Language Models](https://mlsanity.com/paper/2309.05454/) (2023)
- [Evaluating the Evaluators: Are readability metrics good measures of readability?](https://mlsanity.com/paper/2508.19221/) (2025)
- [Readability Reconsidered: A Cross-Dataset Analysis of Reference-Free Metrics](https://mlsanity.com/paper/2510.15345/) (2025)

## Abstract (arXiv)

Flesch Reading Ease (FRE) and the Flesch-Kincaid Grade Level (FKGL) are widely used readability scores for English computed from the same two document statistics, yet their stability on long documents need not imply invariance to lexical composition. Surprisingly, under a topic model with an explicit sentence-boundary token, both scores converge almost surely to deterministic functions of the document topic distribution through just two scalar rates: in the long-text limit, all score variation is mediated by topical composition rather than any residual readability signal. The theory covers both formulae, while the experiments evaluate FKGL. In a fixed admixture with rank[1, q, s] = 3, fibres through interior topic vectors are locally (K-3)-dimensional, whereas regular iso-score level sets are locally (K-2)-dimensional and curved. In out-of-fold evaluation on two balanced corpora, Brown and the written BNC, a topic vector inferred from one document half's content words predicts the other half's FKGL at r = 0.779 and 0.884, respectively. On Brown, adding the topic prediction to genre and mean content-word syllable count yields Delta R2 = 0.002, with a confidence interval spanning zero; on the BNC, the corresponding split-half increment is 0.024, positive in four of five K = 100 fits (median 0.021). Because inferred topics may also absorb genre, register, and style, we do not interpret these results as evidence about human readability or causal effects.