Research

Paper

AI LLM March 06, 2026

Implicit Style Conditioning: A Structured Style-Rewrite Framework for Low-Resource Character Modeling

Authors

Chanhui Zhu

Abstract

Large Language Models (LLMs) have demonstrated impressive capabilities in role-playing (RP); however, small Language Models (SLMs) with highly stylized personas remains a challenge due to data scarcity and the complexity of style disentanglement. Standard Supervised Fine-Tuning (SFT) often captures surface-level semantics while failing to reproduce the intricate syntactic and pragmatic nuances of a character, leading to "Out-Of-Character" (OOC) generation. To address this, we propose a Structured Style-Rewrite Framework that explicitly disentangles style into three interpretable dimensions: lexical signatures (via PMI), syntactic patterns (grounded in PCFG rules), and pragmatic style. Furthermore, we introduce an implicit style conditioning strategy via Chain-of-Thought (CoT) distillation. By leveraging explicit reasoning traces during training as a strong inductive bias, our approach aligns the model's latent representations with structured style features, enabling high-fidelity stylized generation without requiring explicit reasoning tokens during inference. Extensive experiments on a specific high-stylization domain (anime characters) demonstrate that our method enables a Qwen-1.7B model to outperform significantly larger baselines (e.g., 4B Vanilla SFT) in style consistency and semantic fidelity. Our approach offers a data-efficient paradigm for democratizing inference and deployment on consumer hardware.

Metadata

arXiv ID: 2603.05933
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-06
Fetched: 2026-03-09 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.05933v1</id>\n    <title>Implicit Style Conditioning: A Structured Style-Rewrite Framework for Low-Resource Character Modeling</title>\n    <updated>2026-03-06T06:04:47Z</updated>\n    <link href='https://arxiv.org/abs/2603.05933v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.05933v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Large Language Models (LLMs) have demonstrated impressive capabilities in role-playing (RP); however, small Language Models (SLMs) with highly stylized personas remains a challenge due to data scarcity and the complexity of style disentanglement. Standard Supervised Fine-Tuning (SFT) often captures surface-level semantics while failing to reproduce the intricate syntactic and pragmatic nuances of a character, leading to \"Out-Of-Character\" (OOC) generation. To address this, we propose a Structured Style-Rewrite Framework that explicitly disentangles style into three interpretable dimensions: lexical signatures (via PMI), syntactic patterns (grounded in PCFG rules), and pragmatic style. Furthermore, we introduce an implicit style conditioning strategy via Chain-of-Thought (CoT) distillation. By leveraging explicit reasoning traces during training as a strong inductive bias, our approach aligns the model's latent representations with structured style features, enabling high-fidelity stylized generation without requiring explicit reasoning tokens during inference. Extensive experiments on a specific high-stylization domain (anime characters) demonstrate that our method enables a Qwen-1.7B model to outperform significantly larger baselines (e.g., 4B Vanilla SFT) in style consistency and semantic fidelity. Our approach offers a data-efficient paradigm for democratizing inference and deployment on consumer hardware.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-06T06:04:47Z</published>\n    <arxiv:comment>26 pages, 4 figures. Preprint</arxiv:comment>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Chanhui Zhu</name>\n    </author>\n  </entry>"
}