# Audience-Centric Natural Language Generation via Style Infusion

arXiv: https://arxiv.org/abs/2301.10283 · HTML: https://mlsanity.com/paper/2301.10283/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 59 references that are in the map.
- First posted on arXiv 24 Jan 2023.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Style Transfer from Non-Parallel Text by Cross-Alignment](https://mlsanity.com/paper/1705.09655/) (2017)
- [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://mlsanity.com/paper/1804.06437/) (2018)
- [Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions](https://mlsanity.com/paper/1602.01103/) (2016)
- [Generating Sentences by Editing Prototypes](https://mlsanity.com/paper/1709.08878/) (2017)
- [Unsupervised Text Style Transfer using Language Models as Discriminators](https://mlsanity.com/paper/1805.11749/) (2018)
- [Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Models](https://mlsanity.com/paper/1707.01161/) (2017)
- [Hooks in the Headline: Learning to Generate Headlines with Controlled Styles](https://mlsanity.com/paper/2004.01980/) (2020)
- [Regularizing Neural Machine Translation by Target-bidirectional Agreement](https://mlsanity.com/paper/1808.04064/) (2018)
- [IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation](https://mlsanity.com/paper/1901.11333/) (2019)
- [Exploring the Role of Argument Structure in Online Debate Persuasion](https://mlsanity.com/paper/2010.03538/) (2020)
- [Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning](https://mlsanity.com/paper/1909.03582/) (2019)
- [Semi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information Maximization](https://mlsanity.com/paper/2010.05090/) (2020)
- [Persuasive Natural Language Generation -- A Literature Review](https://mlsanity.com/paper/2101.05786/) (2021)
- [When is it Better to Compare than to Score?](https://mlsanity.com/paper/1406.6618/) (2014)
- [Unsupervised Controllable Text Formalization](https://mlsanity.com/paper/1809.04556/) (2018)
- [BlaBla: Linguistic Feature Extraction for Clinical Analysis in Multiple Languages](https://mlsanity.com/paper/2005.10219/) (2020)

## Built on by (most cited first, 5 of 5)

- [Measuring and Improving Persuasiveness of Large Language Models](https://mlsanity.com/paper/2410.02653/) (2024)
- [GRAVITY: A Framework for Personalized Text Generation via Profile-Grounded Synthetic Preferences](https://mlsanity.com/paper/2510.11952/) (2025)
- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)
- [Text Fact Transfer](https://mlsanity.com/paper/2310.14486/) (2023)
- [CWF: A Collaborative Writing Framework for Personalized and Reliable Popular Science Writing](https://mlsanity.com/paper/2609.06126/) (2026)

## Abstract (arXiv)

Adopting contextually appropriate, audience-tailored linguistic styles is critical to the success of user-centric language generation systems (e.g., chatbots, computer-aided writing, dialog systems). While existing approaches demonstrate textual style transfer with large volumes of parallel or non-parallel data, we argue that grounding style on audience-independent external factors is innately limiting for two reasons. First, it is difficult to collect large volumes of audience-specific stylistic data. Second, some stylistic objectives (e.g., persuasiveness, memorability, empathy) are hard to define without audience feedback. In this paper, we propose the novel task of style infusion - infusing the stylistic preferences of audiences in pretrained language generation models. Since humans are better at pairwise comparisons than direct scoring - i.e., is Sample-A more persuasive/polite/empathic than Sample-B - we leverage limited pairwise human judgments to bootstrap a style analysis model and augment our seed set of judgments. We then infuse the learned textual style in a GPT-2 based text generator while balancing fluency and style adoption. With quantitative and qualitative assessments, we show that our infusion approach can generate compelling stylized examples with generic text prompts. The code and data are accessible at https://github.com/CrowdDynamicsLab/StyleInfusion.