用100条专家思维链，让小模型学会创作质量对齐。
Creative Quality Alignment: Expert Tacit Knowledge Transfer via Chain-of-Thought Fine-Tuning
- 仅用约100条专家思维链标注数据，实现创作质量对齐。
- 发现现有对齐数据偏重手工技能，忽视受众与现实逻辑。
- 揭示生成与评价的结构对偶性，解释小样本有效原因。
本文实现了Calibrated Surprise（Zou & Xu, 2026a）提出的创造质量度量的实证应用。研究核心问题是：该数学假设在工程层面是否成立？为使结论尽可能普适，我们采用最严苛的工程条件：低数据成本与小型基础模型。训练数据来自约100条由BC Protocol（Zou & Xu, 2026b）生成的专家思维链（CoT）注释。我们识别出一种数据偏差：当前公开对齐数据集普遍偏向工艺类知识，而受众建模与现实逻辑覆盖系统性薄弱。我们提出“创作质量对齐”（Creative Quality Alignment, CQA）这一工程方法类别。此外，提供一项支持性理论观察：在具有单一条件分布架构的大语言模型中，校准评价侧会通过架构对偶性自动传递至生成侧。这正是约100个思维链样本即可生效的结构性原因，而非如LIMA（Zhou et al., 2023）般的纯经验现象。
原文摘要 · Abstract (English)
This paper provides an empirical implementation of the creative quality metric proposed in Calibrated Surprise (Zou & Xu, 2026a). The question this paper addresses is: does this mathematical claim hold at the engineering level? To make the answer as general as possible, we deliberately choose the strictest engineering conditions: low data cost and a small base model. Training data comes from approximately 100 expert chain-of-thought (CoT) annotations produced by the BC Protocol (Zou & Xu, 2026b). We also identify a data bias: most publicly available alignment datasets are skewed toward craft-related knowledge, while audience modeling and reality-logic coverage are systematically weak. We use the term Creative Quality Alignment (CQA) to describe this class of engineering methods. We also offer a supporting theoretical observation: in an LLM with a single conditional distribution architecture, calibrating the appreciation side automatically transfers to the generation side via architectural duality. This is the structural reason why ~100 CoT examples are sufficient -- not a purely empirical observation like LIMA (Zhou et al., 2023).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。