个性化文本生成与细粒度语言控制
Personalized Text Generation with Fine-Grained Linguistic Control
AI总结：
本文针对大语言模型可控文本生成中细粒度语言属性（如词汇和句法）控制不足的问题，提出新基准以训练和评估模型，并系统分析多种大模型性能，公开代码、数据和预训练模型。
摘要：
随着大语言模型文本生成能力的日益突出，近期研究聚焦于控制生成文本的特定方面以使其更具个性化。然而，大多数可控文本生成研究侧重于控制内容或建模反映作者写作风格的高层/粗粒度属性，如正式度、领域或情感。本文中，我们专注于控制跨越多个语言维度的细粒度属性，例如词汇和句法属性。我们引入了一个新颖的基准来训练生成模型并评估其基于多个细粒度语言属性生成个性化文本的能力。我们系统地研究了各种大语言模型在我们基准上的性能，并从影响其性能的因素中汲取见解。我们公开了我们的代码、数据和预训练模型。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
