LiteraryTaste：面向创意写作个性化的偏好数据集
LiteraryTaste: A Preference Dataset for Creative Writing Personalization
AI总结：
针对创意写作LLM未适配用户偏好的问题，本文构建LiteraryTaste数据集（含60人的陈述偏好与100对文本的显示偏好标注），实验表明微调Transformer编码器可有效建模偏好，且陈述偏好效用有限，为个性化创意写作技术奠定基础。
摘要：
人们具有不同的创意写作偏好，面向此类任务的大型语言模型（LLMs）可通过适配每位用户的偏好而获益。然而，这些模型通常在将多样个人品味视为单一整体的数据集上训练。为推动个性化创意写作LLMs的开发，我们引入LiteraryTaste——一个包含60人阅读偏好的数据集，每人需完成：1）自我报告阅读习惯与品味（陈述偏好）；2）对100对创意写作短文标注偏好（显示偏好）。借助该数据集，我们发现：1）人们的创意写作偏好存在差异；2）微调Transformer编码器在建模个人和集体显示偏好时，准确率分别可达75.8%和67.7%；3）陈述偏好在建模显示偏好时的效用有限。通过LLM驱动的可解释性流程，我们分析了人们偏好的差异方式。我们希望这项工作能成为个性化创意写作技术的基石。
英文摘要：
People have different creative writing preferences, and large language models (LLMs) for these tasks can benefit from adapting to each user's preferences. However, these models are often trained over a dataset that considers varying personal tastes as a monolith. To facilitate developing personalized creative writing LLMs, we introduce LiteraryTaste, a dataset of reading preferences from 60 people, where each person: 1) self-reported their reading habits and tastes (stated preference), and 2) annotated their preferences over 100 pairs of short creative writing texts (revealed preference). With our dataset, we found that: 1) people diverge on creative writing preferences, 2) finetuning a transformer encoder could achieve 75.8% and 67.7% accuracy when modeling personal and collective revealed preferences, and 3) stated preferences had limited utility in modeling revealed preferences. With an LLM-driven interpretability pipeline, we analyzed how people's preferences vary. We hope our work serves as a cornerstone for personalizing creative writing technologies.
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。
