# Unsupervised Text Style Transfer for Controllable Intensity

arXiv: https://arxiv.org/abs/2601.01060 · HTML: https://mlsanity.com/paper/2601.01060/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 3 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](https://mlsanity.com/paper/2205.12548/) (2022)
- [Reinforcement learning](https://mlsanity.com/paper/2405.10369/) (2024)
- [Delete, Retrieve, Generate: A Simple Approach to Sentiment and Style Transfer](https://mlsanity.com/paper/1804.06437/) (2018)
- [Style Transfer in Text: Exploration and Evaluation](https://mlsanity.com/paper/1711.06861/) (2017)
- [Style Transfer Through Back-Translation](https://mlsanity.com/paper/1804.09000/) (2018)
- [Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer](https://mlsanity.com/paper/1908.09368/) (2019)
- [A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer](https://mlsanity.com/paper/1905.10060/) (2019)
- [Evaluating Style Transfer for Text](https://mlsanity.com/paper/1904.02295/) (2019)
- [Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus](https://mlsanity.com/paper/1903.10671/) (2019)
- [Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality Transfer](https://mlsanity.com/paper/2110.10668/) (2021)
- [Generating Summaries with Controllable Readability Levels](https://mlsanity.com/paper/2310.10623/) (2023)
- [Stable Style Transformer: Delete and Generate Approach with Encoder-Decoder for Text Style Transfer](https://mlsanity.com/paper/2005.12086/) (2020)
- [Evaluating Text Style Transfer Evaluation: Are There Any Reliable Metrics?](https://mlsanity.com/paper/2502.04718/) (2025)
- [An LLM-Enhanced Adversarial Editing System for Lexical Simplification](https://mlsanity.com/paper/2402.14704/) (2024)
- [ProSwitch: Knowledge-Guided Instruction Tuning to Switch Between Professional and Non-Professional Responses](https://mlsanity.com/paper/2403.09131/) (2024)

## Built on by (most cited first, 1 of 1)

- [RT-SFT: Text Style Transfer from Non-Parallel Corpora by Roundtrip Translation](https://mlsanity.com/paper/2602.15013/) (2026)

## Abstract (arXiv)

Unsupervised Text Style Transfer (UTST) aims to build a system to transfer the stylistic properties of a given text without parallel text pairs. Compared with text transfer between style polarities, UTST for controllable intensity is more challenging due to the subtle differences in stylistic features across different intensity levels. Faced with the challenges posed by the lack of parallel data and the indistinguishability between adjacent intensity levels, we propose a SFT-then-PPO paradigm to fine-tune an LLM. We first fine-tune the LLM with synthesized parallel data. Then, we further train the LLM with PPO, where the rewards are elaborately designed for distinguishing the stylistic intensity in hierarchical levels. Both the global and local stylistic features are considered to formulate the reward functions. The experiments on two UTST benchmarks showcase that both rewards have their advantages and applying them to LLM fine-tuning can effectively improve the performance of an LLM backbone based on various evaluation metrics. Even for close levels of intensity, we can still observe the noticeable stylistic difference between the generated text.