结构化风格重写与思维链规划用于低资源字符对话
Structured Style-Rewrite with Chain-of-Thought Planning for Low-Resource Character Dialogue
AI总结：
本文提出了一种结构化风格重写框架，结合思维链规划，以解决低资源条件下中文字符驱动生成中的风格分离问题，通过分解角色风格为可解释的格式签名、语法和语用维度，并利用思维链监督进行显式风格规划，实验表明该方法在保持语义忠实性的同时提升了风格质量。
摘要：
将小型语言模型（SLMs）应用于中文字符驱动生成仍然具有挑战性，因为数据稀缺和分离角色风格困难。标准监督微调（SFT）通常捕捉到表层语义，但会产生频繁的越界输出（OOC）。我们将此问题框架为受控的句子级风格重写任务，该任务将风格质量与对话情境管理分离。我们提出了一种结构化风格重写框架，将角色风格分解为可解释的格式签名、语法和语用维度，并结合思维链（CoT）监督进行显式风格规划。一个CoT共享直接偏好优化（DPO）阶段进一步通过确保偏好学习目标输出层面的风格执行而非推理轨迹差异来对齐风格规划与表层实现。在八个角色四个不同源领域的实验中，我们的方法使Qwen3-1.7B模型在有效风格得分上达到0.632，同时保持强语义忠实性（0.878），在评估系统中处于帕累托前沿，并在消费级硬件上显著优于更大的基线（如GLM-4.7）
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
