# Structured Style-Rewrite with Chain-of-Thought Planning for Low-Resource Character Dialogue

arXiv: https://arxiv.org/abs/2603.05933 · HTML: https://mlsanity.com/paper/2603.05933/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 13 of 13)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step](https://mlsanity.com/paper/2405.14838/) (2024)
- [ChatHaruhi: Reviving Anime Character in Reality via Large Language Model](https://mlsanity.com/paper/2308.09597/) (2023)
- [In Defense of RAG in the Era of Long-Context Language Models](https://mlsanity.com/paper/2409.01666/) (2024)
- [Controlling Style in Generated Dialogue](https://mlsanity.com/paper/2009.10855/) (2020)
- [Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few Utterances](https://mlsanity.com/paper/2204.10825/) (2022)
- [Structuring Latent Spaces for Stylized Response Generation](https://mlsanity.com/paper/1909.05361/) (2019)
- [Conversation Style Transfer using Few-Shot Learning](https://mlsanity.com/paper/2302.08362/) (2023)
- [Stylistic Retrieval-based Dialogue System with Unparallel Training Data](https://mlsanity.com/paper/2109.05477/) (2021)
- [SLIM-LLMs: Modeling of Style-Sensory Language RelationshipsThrough Low-Dimensional Representations](https://mlsanity.com/paper/2508.02901/) (2025)

## Abstract (arXiv)

Applying Small Language Models (SLMs) to Chinese character-driven generation remains challenging due to data scarcity and the difficulty of disentangling character style. Standard Supervised Fine-Tuning (SFT) often captures surface-level semantics but produces frequent Out-Of-Character (OOC) outputs. We frame this as a controlled sentence-level style rewriting task, which isolates stylistic quality from dialogue context management. We propose a Structured Style-Rewrite Framework that decomposes character style into interpretable format signature, syntactic, and pragmatic dimensions, combined with Chain-of-Thought (CoT) supervision for explicit style planning. A CoT-Shared Direct Preference Optimization (DPO) stage further aligns style planning with surface realization by ensuring preference learning targets output-level style execution rather than reasoning trace differences. Experiments across eight characters from four diverse source domains demonstrate that our method enables a Qwen3-1.7B model to achieve a Valid Style Score of 0.632 while maintaining strong semantic fidelity (0.878), placing on the Pareto frontier among the evaluated systems and outperforming significantly larger baselines (e.g., GLM-4.7) on consumer hardware.