发表机构
MBZUAI; Shandong University; ByteDance; Tohoku University; RIKEN（穆罕默德·本·扎耶德人工智能大学; 山东大学; 字节跳动; 东北大学; 理化学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有作者个性化文本生成方法成本高、难解释、泛化差的问题，提出LiteraryBigFive框架，将作者写作特征映射到统一可解释空间，结合可解释引导机制实现个性化生成，提升表达力且符合文学共识。
AI 中文摘要
作者和文学写作的个性化文本生成对自适应写作助手、创意支持工具及计算文学分析等应用至关重要。然而，现有作者建模与个性化方法常将写作行为表示为独立标签，需为每位作者或风格类别收集大规模语料库或进行微调，此类方案成本高、难以解释，且作者间泛化能力差。受大五人格模型的人格维度视角启发，我们提出框架LiteraryBigFive，将作者写作特征重新表述为统一可解释空间内的坐标。在该空间中，我们通过作者撰写文本与中性文本的激活空间对比推导每个可解释轴（如古典性、情感性），得到独特的风格维度，使文本或作者可在五维系统中定位。除定位不同作者外，我们还引入可解释引导机制，自适应引导文本生成至目标坐标以执行作者个性化写作。实验结果显示，LiteraryBigFive在保留语义保真度的同时提升了作者表达力；推导得到的作者各轴得分与现实世界文学共识高度相关，能为作者特定生成行为提供透明可解释的说明。
英文摘要
Personalized text generation for authors and literary writing is essential for applications such as adaptive writing assistants, creative support tools, and computational literary analysis. However, existing approaches to author modeling and personalization often represent writing behavior as independent labels, requiring large-scale corpus collection or fine-tuning for each author or stylistic category. Such formulations are costly, difficult to interpret, and poorly suited for generalizing across authors. Inspired by the Big Five model's dimensional view of personality, we propose LiteraryBigFive, a framework that reframes authorial writing characteristics as coordinates within a unified and interpretable space. In this space, we derive each interpretable axis (e.g., Classicism, Emotionality) from activation-space contrasts between author-written and neutral passages, yielding distinct stylistic dimensions that allow texts or authors to be positioned within a five-dimensional system. Beyond localizing different authors, we further introduce an interpretable steering mechanism, which adaptively guides text generation toward target coordinates to perform author-personalized writing. Experimental results show that LiteraryBigFive improves authorial expressiveness while preserving semantic fidelity. The derived author per-axis scores strongly correlate with real-world literary consensus, offering transparent and interpretable explanations of author-specific generation behavior: https://github.com/Znull-1220/LiteraryBigFive.
CommentsEMNLP 2026 Findings, Camera Ready
