mlsanityData to 7 Oct 2026

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

arXiv 2603.05933 ↗First posted 6 Mar 2026cs.CL cs.LGcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

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.

Key facts. No citing papers in the map yet (data through 7 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.

Builds on

13 of 25 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models8 Aug
  2. 2025Qwen3 Technical Report14 May
  3. 2024DeepSeek-V3 Technical Report27 Dec

Other references · 10

  1. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
  2. 2024From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Stepcited by 225
  3. 2023ChatHaruhi: Reviving Anime Character in Reality via Large Language Modelcited by 57
  4. 2024In Defense of RAG in the Era of Long-Context Language Modelscited by 52
  5. 2020Controlling Style in Generated Dialoguecited by 38
  6. 2022Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few Utterancescited by 32
  7. 2019Structuring Latent Spaces for Stylized Response Generationcited by 25
  8. 2023Conversation Style Transfer using Few-Shot Learningcited by 4
  9. 2021Stylistic Retrieval-based Dialogue System with Unparallel Training Datacited by 2
  10. 2025SLIM-LLMs: Modeling of Style-Sensory Language RelationshipsThrough Low-Dimensional Representationscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Dr Genre: Reinforcement Learning from Decoupled LLM Feedback for Generic Text Rewriting
  2. 2022Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters
  3. 2025StyleBench: Evaluating thinking styles in Large Language Models
  4. 2023RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting
  5. 2026Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach
  6. 2025StyleRec: A Benchmark Dataset for Prompt Recovery in Writing Style Transformation
  7. 2026From Script to Drama: An Agentic Framework for Controllable Multi-Speaker Dialogue TTS
  8. 2023Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs