# Implementing Long Text Style Transfer with LLMs through Dual-Layered Sentence and Paragraph Structure Extraction and Mapping

arXiv: https://arxiv.org/abs/2505.07888 · HTML: https://mlsanity.com/paper/2505.07888/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 33 references that are in the map.
- First posted on arXiv 11 May 2025.

## Builds on (most cited first, 26 of 26)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [Style Transfer from Non-Parallel Text by Cross-Alignment](https://mlsanity.com/paper/1705.09655/) (2017)
- [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)
- [Deep Learning for Text Style Transfer: A Survey](https://mlsanity.com/paper/2011.00416/) (2020)
- [T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step](https://mlsanity.com/paper/2312.14033/) (2023)
- [Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning](https://mlsanity.com/paper/2402.04401/) (2024)
- [A Probabilistic Formulation of Unsupervised Text Style Transfer](https://mlsanity.com/paper/2002.03912/) (2020)
- [Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities](https://mlsanity.com/paper/2409.03444/) (2024)
- [PaSa: An LLM Agent for Comprehensive Academic Paper Search](https://mlsanity.com/paper/2501.10120/) (2025)
- [Polite Dialogue Generation Without Parallel Data](https://mlsanity.com/paper/1805.03162/) (2018)
- [AxCell: Automatic Extraction of Results from Machine Learning Papers](https://mlsanity.com/paper/2004.14356/) (2020)
- [CoSER: A Comprehensive Literary Dataset and Framework for Training and Evaluating LLM Role-Playing and Persona Simulation](https://mlsanity.com/paper/2502.09082/) (2025)
- [Style-Specific Neurons for Steering LLMs in Text Style Transfer](https://mlsanity.com/paper/2410.00593/) (2024)
- [Sentence-Level Content Planning and Style Specification for Neural Text Generation](https://mlsanity.com/paper/1909.00734/) (2019)
- [Adapting Language Models for Non-Parallel Author-Stylized Rewriting](https://mlsanity.com/paper/1909.09962/) (2019)
- [Distilling Text Style Transfer With Self-Explanation From LLMs](https://mlsanity.com/paper/2403.01106/) (2024)
- [CAT-LLM: Style-enhanced Large Language Models with Text Style Definition for Chinese Article-style Transfer](https://mlsanity.com/paper/2401.05707/) (2024)
- [DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue](https://mlsanity.com/paper/2502.13847/) (2025)
- [Unsupervised Text Style Transfer via LLMs and Attention Masking with Multi-way Interactions](https://mlsanity.com/paper/2402.13647/) (2024)
- [Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style](https://mlsanity.com/paper/2410.03848/) (2024)
- [LMStyle Benchmark: Evaluating Text Style Transfer for Chatbots](https://mlsanity.com/paper/2403.08943/) (2024)
- [Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation](https://mlsanity.com/paper/2409.12411/) (2024)

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

- [The Hitchhiker's Guide to Agentic AI: From Foundations to Systems](https://mlsanity.com/paper/2606.24937/) (2026)

## Abstract (arXiv)

This paper addresses the challenge in long-text style transfer using zero-shot learning of large language models (LLMs), proposing a hierarchical framework that combines sentence-level stylistic adaptation with paragraph-level structural coherence. We argue that in the process of effective paragraph-style transfer, to preserve the consistency of original syntactic and semantic information, it is essential to perform style transfer not only at the sentence level but also to incorporate paragraph-level semantic considerations, while ensuring structural coherence across inter-sentential relationships. Our proposed framework, ZeroStylus, operates through two systematic phases: hierarchical template acquisition from reference texts and template-guided generation with multi-granular matching. The framework dynamically constructs sentence and paragraph template repositories, enabling context-aware transformations while preserving inter-sentence logical relationships. Experimental evaluations demonstrate significant improvements over baseline methods, with structured rewriting achieving 6.90 average score compared to 6.70 for direct prompting approaches in tri-axial metrics assessing style consistency, content preservation, and expression quality. Ablation studies validate the necessity of both template hierarchies during style transfer, showing higher content preservation win rate against sentence-only approaches through paragraph-level structural encoding, as well as direct prompting method through sentence-level pattern extraction and matching. The results establish new capabilities for coherent long-text style transfer without requiring parallel corpora or LLM fine-tuning.