# Learning to Generate Text in Arbitrary Writing Styles

arXiv: https://arxiv.org/abs/2312.17242 · HTML: https://mlsanity.com/paper/2312.17242/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 49 references that are in the map.
- First posted on arXiv 28 Dec 2023.

## Builds on (most cited first, 30 of 38)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Evaluation of Text Generation: A Survey](https://mlsanity.com/paper/2006.14799/) (2020)
- [Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer](https://mlsanity.com/paper/1803.06535/) (2018)
- [Reformulating Unsupervised Style Transfer as Paraphrase Generation](https://mlsanity.com/paper/2010.05700/) (2020)
- [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://mlsanity.com/paper/2110.07205/) (2021)
- [Deep Learning for Text Style Transfer: A Survey](https://mlsanity.com/paper/2011.00416/) (2020)
- [Style Transfer Through Back-Translation](https://mlsanity.com/paper/1804.09000/) (2018)
- [A Recipe For Arbitrary Text Style Transfer with Large Language Models](https://mlsanity.com/paper/2109.03910/) (2021)
- [Same Author or Just Same Topic? Towards Content-Independent Style Representations](https://mlsanity.com/paper/2204.04907/) (2022)
- [Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer](https://mlsanity.com/paper/1908.09368/) (2019)
- [Politeness Transfer: A Tag and Generate Approach](https://mlsanity.com/paper/2004.14257/) (2020)
- [Towards Robust and Privacy-preserving Text Representations](https://mlsanity.com/paper/1805.06093/) (2018)
- [Mix and Match: Learning-free Controllable Text Generation using Energy Language Models](https://mlsanity.com/paper/2203.13299/) (2022)
- [Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelation](https://mlsanity.com/paper/2106.00131/) (2021)
- [Gradient-Based Constrained Sampling from Language Models](https://mlsanity.com/paper/2205.12558/) (2022)
- [Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Models](https://mlsanity.com/paper/1707.01161/) (2017)
- [XFORMAL: A Benchmark for Multilingual Formality Style Transfer](https://mlsanity.com/paper/2104.04108/) (2021)

## Built on by (most cited first, 9 of 9)

- [StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples](https://mlsanity.com/paper/2410.12757/) (2024)
- [TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings](https://mlsanity.com/paper/2406.15586/) (2024)
- [SARD: A Human-AI Collaborative Story Generation](https://mlsanity.com/paper/2403.01575/) (2024)
- [Attacks on Machine-Text Detectors Retain Stylistic Fingerprints](https://mlsanity.com/paper/2505.14608/) (2025)
- [SAG: Style-Aligned Article Generation via Model Collaboration](https://mlsanity.com/paper/2410.03137/) (2024)
- [Learning Extrapolative Sequence Transformations from Markov Chains](https://mlsanity.com/paper/2505.20251/) (2025)
- [MetaSynth: Multi-Agent Metadata Generation from Implicit Feedback in Black-Box Systems](https://mlsanity.com/paper/2510.01523/) (2025)
- [STEB: Style Text Embedding Benchmark](https://mlsanity.com/paper/2606.31741/) (2026)
- [HyperStyler: Low-resource Authorship Style Transfer via Context-aware Style Navigation and Hypernetworks](https://mlsanity.com/paper/2609.02772/) (2026)

## Abstract (arXiv)

Prior work in style-controlled text generation has focused on tasks such as emulating the style of prolific literary authors, producing formal or informal text, and mitigating toxicity of generated text. Plentiful demonstrations of these styles are available, and as a result modern language models are often able to emulate them, either via prompting or discriminative control. However, in applications such as writing assistants, it is desirable for language models to produce text in an author-specific style on the basis of a potentially small writing sample. For example, someone writing in a particular dialect may prefer writing suggestions that retain the same dialect. We find that instruction-tuned language models can struggle to reproduce author-specific style demonstrated in a prompt. Instead, we propose to guide a language model to generate text in a target style using contrastively-trained representations that capture stylometric features. Our approach (StyleMC) combines an author-adapted language model with sequence-level inference to improve stylistic consistency, and is found to be effective in a variety of conditions, including unconditional generation and style transfer. Additionally, we find that the proposed approach can serve as an effective anonymization method, by editing a document to mask authorship while preserving the original meaning