# Adapting Language Models for Non-Parallel Author-Stylized Rewriting

arXiv: https://arxiv.org/abs/1909.09962 · HTML: https://mlsanity.com/paper/1909.09962/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2019.

## Built on by (most cited first, 23 of 23)

- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer](https://mlsanity.com/paper/2104.05196/) (2021)
- [Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data](https://mlsanity.com/paper/2406.13843/) (2024)
- [Are You Robert or RoBERTa? Deceiving Online Authorship Attribution Models Using Neural Text Generators](https://mlsanity.com/paper/2203.09813/) (2022)
- [A Call for Standardization and Validation of Text Style Transfer Evaluation](https://mlsanity.com/paper/2306.00539/) (2023)
- [CAT-LLM: Style-enhanced Large Language Models with Text Style Definition for Chinese Article-style Transfer](https://mlsanity.com/paper/2401.05707/) (2024)
- [StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content Enhancing](https://mlsanity.com/paper/2208.13423/) (2022)
- [Controlling Styles in Neural Machine Translation with Activation Prompt](https://mlsanity.com/paper/2212.08909/) (2022)
- [Customizing Large Language Model Generation Style using Parameter-Efficient Finetuning](https://mlsanity.com/paper/2409.04574/) (2024)
- [DRAG: Director-Generator Language Modelling Framework for Non-Parallel Author Stylized Rewriting](https://mlsanity.com/paper/2101.11836/) (2021)
- [From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey](https://mlsanity.com/paper/2110.15871/) (2021)
- [Summaformers @ LaySumm 20, LongSumm 20](https://mlsanity.com/paper/2101.03553/) (2021)
- [DYPLODOC: Dynamic Plots for Document Classification](https://mlsanity.com/paper/2107.12226/) (2021)
- [Low Resource Style Transfer via Domain Adaptive Meta Learning](https://mlsanity.com/paper/2205.12475/) (2022)
- [SC2: Towards Enhancing Content Preservation and Style Consistency in Long Text Style Transfer](https://mlsanity.com/paper/2406.04578/) (2024)
- [Incorporating Stylistic Lexical Preferences in Generative Language Models](https://mlsanity.com/paper/2010.11553/) (2020)
- [Adapter-TST: A Parameter Efficient Method for Multiple-Attribute Text Style Transfer](https://mlsanity.com/paper/2305.05945/) (2023)
- [Specializing Small Language Models towards Complex Style Transfer via Latent Attribute Pre-Training](https://mlsanity.com/paper/2309.10929/) (2023)
- [Style-News: Incorporating Stylized News Generation and Adversarial Verification for Neural Fake News Detection](https://mlsanity.com/paper/2401.15509/) (2024)
- [Pluggable Neural Machine Translation Models via Memory-augmented Adapters](https://mlsanity.com/paper/2307.06029/) (2023)
- [Implementing Long Text Style Transfer with LLMs through Dual-Layered Sentence and Paragraph Structure Extraction and Mapping](https://mlsanity.com/paper/2505.07888/) (2025)
- [Unsupervised Neural Stylistic Text Generation using Transfer learning and Adapters](https://mlsanity.com/paper/2210.03264/) (2022)
- [StyleAdaptedLM: Enhancing Instruction Following Models with Efficient Stylistic Transfer](https://mlsanity.com/paper/2507.18294/) (2025)

## Abstract (arXiv)

Given the recent progress in language modeling using Transformer-based neural models and an active interest in generating stylized text, we present an approach to leverage the generalization capabilities of a language model to rewrite an input text in a target author's style. Our proposed approach adapts a pre-trained language model to generate author-stylized text by fine-tuning on the author-specific corpus using a denoising autoencoder (DAE) loss in a cascaded encoder-decoder framework. Optimizing over DAE loss allows our model to learn the nuances of an author's style without relying on parallel data, which has been a severe limitation of the previous related works in this space. To evaluate the efficacy of our approach, we propose a linguistically-motivated framework to quantify stylistic alignment of the generated text to the target author at lexical, syntactic and surface levels. The evaluation framework is both interpretable as it leads to several insights about the model, and self-contained as it does not rely on external classifiers, e.g. sentiment or formality classifiers. Qualitative and quantitative assessment indicates that the proposed approach rewrites the input text with better alignment to the target style while preserving the original content better than state-of-the-art baselines.