As the text generation capabilities of large language models become increasingly prominent, recent studies have focused on controlling particular aspects of the generated text to make it more personalized. However, most research on controllable text generation focuses on controlling the content or modeling specific high-level/coarse-grained attributes that reflect authors' writing styles, such as formality, domain, or sentiment. In this paper, we focus on controlling fine-grained attributes spanning multiple linguistic dimensions, such as lexical and syntactic attributes. We introduce a novel benchmark to train generative models and evaluate their ability to generate personalized text based on multiple fine-grained linguistic attributes. We systematically investigate the performance of various large language models on our benchmark and draw insights from the factors that impact their performance. We make our code, data, and pretrained models publicly available.

翻译：随着大语言模型文本生成能力的日益凸显，近期研究开始关注如何控制生成文本的特定方面以实现个性化。然而，当前可控文本生成领域的大多数工作主要聚焦于内容控制或建模反映作者写作风格的高层/粗粒度属性（如正式程度、领域或情感倾向）。本文专注于控制跨多个语言维度的细粒度属性，包括词汇属性和句法属性。我们提出一个新的基准测试，用于训练生成模型并评估其基于多维度细粒度语言属性生成个性化文本的能力。我们系统性地研究了各类大语言模型在此基准测试中的表现，并深入分析了影响其性能的关键因素。我们将公开我们的代码、数据和预训练模型。