# Structured Style-Rewrite with Chain-of-Thought Planning for Low-Resource Character Dialogue Source: [Structured Style-Rewrite with Chain-of-Thought Planning for Low-Resource Character Dialogue]() Collection index: [llms.txt]() Data updated: 2026-05-21T05:00:13.694Z Authors: Chanhui Zhu Published: 2026-03-06T06:04:47.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Style Transfer on Hybrid (test)](): Style Transfer; Hybrid (test); Semantic Score: 0.88. - [Classification on Character Archetype Classification Dataset](): Classification; Character Archetype Classification Dataset; Macro-F1: 79. - [Dialogue Style Transfer on Anime-style dialogue human evaluation set (test)](): Dialogue Style Transfer; Anime-style dialogue human evaluation set (test); Semantic Coherence Score: 4.24. - [Dialogue Style Transfer on Anime-style dialogue evaluation set (test)](): Dialogue Style Transfer; Anime-style dialogue evaluation set (test); Semantic Similarity: 4.29. ## Original sources and implementation [Original paper]() [PDF]()