AI 中文总结
本研究提出PAUSE可编辑策略制品，用于控制长篇文化故事改编的文化决策，实验显示人类对该策略的编辑可有效传递到章节文本，提升了AI文化改编的可检查性与可争议性。
AI 中文摘要
生成式AI系统越来越多地介入文化改编工作，但它们的文化决策通常隐藏在提示词、瞬时模型规划或最终文本中。本研究提出PAUSE（Pause-And-Update Strategy Editing，即暂停与更新策略编辑），这是一种将可编辑的改编策略作为人类控制界面的干预方法，用于控制长篇故事改编中的文化决策。该策略是一种结构化制品，可被检查、编辑，随后通过下游的角色、实体和章节定位阶段投射出来。在两部中文来源的连载小说中，我们测试人类对该策略的编辑是否会传播到章节级文本中。在9次编辑与对照章节的对比中，评审在所有9次对比中都选择了编辑策略生成的输出；标记审计显示，8/9的编辑输出中存在目标标记，而9个对照输出中均无；禁止标记不存在于编辑输出中，却存在于所有对照输出中。我们将这些结果视为烟标编辑依从性研究，并非声称这些输出具有文化权威性或文学质量提升。PAUSE提供了一种实用方法，可让AI介导的文化改编在决策传播至长篇生成前更具可检查性和可争议性。
英文摘要
Generative AI systems increasingly mediate cultural adaptation, but their cultural decisions are often hidden inside prompts, transient model plans, or final prose. We study PAUSE (Pause-And-Update Strategy Editing), an intervention that exposes an editable adaptation strategy as a human control surface for cultural decisions in long-form story adaptation. The strategy is a structured artifact that can be inspected, edited, and then projected through downstream character, entity, and chapter-localization stages. In two Chinese-source serialized novels, we test whether human edits to this strategy propagate into chapter-level prose. Across 9 edited-vs-control chapter comparisons, judges select the edited-strategy output in all 9; a marker audit shows target markers in 8/9 edited outputs and 0/9 controls, with forbidden markers absent from edited outputs and present in all controls. We frame these results as a smoke-scale edit-adherence study, not a claim that the outputs are culturally authoritative or literary-quality improvements. PAUSE offers one practical way to make AI-mediated cultural adaptation more inspectable and contestable before decisions propagate through long-form generation.
Comments6 pages, 1 figure, 3 tables. Accepted at the 1st Workshop on Culture x AI: Evaluating AI as a Cultural Technology, ICML 2026. Project page: https://abdur75648.github.io/pause/
