写作路径导航：基于大纲引导的大型语言模型文本生成
Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models
AI总结：
针对LLM生成文本难以满足用户意图的问题，提出WritingPath框架，利用显式大纲引导生成高质量目标导向文本，并通过多样化数据集和全面评估验证其有效性。
摘要：
大型语言模型（LLMs）已深刻影响写作过程，通过在内容创作平台中与人类协作来提升生产力。然而，生成高质量、符合用户意图的文本以满足现实世界的内容创作需求仍然具有挑战性。我们提出WritingPath，一个利用显式大纲引导LLMs生成目标导向、高质量文本的框架。我们的方法借鉴了结构化写作规划和推理路径的思想，重点在于整个写作过程中反映用户意图。为了在现实场景中验证我们的方法，我们从非结构化博客文章中构建了一个多样化的数据集，用于基准测试写作性能，并引入了一个全面的评估框架，用于评估大纲和生成文本的质量。我们使用多种LLMs进行的评估表明，根据LLMs和专业写作者的评估，WritingPath方法显著提升了文本质量。
英文摘要：
Large Language Models (LLMs) have impacted the writing process, enhancing productivity by collaborating with humans in content creation platforms. However, generating high-quality, user-aligned text to satisfy real-world content creation needs remains challenging. We propose WritingPath, a framework that uses explicit outlines to guide LLMs in generating goal-oriented, high-quality text. Our approach draws inspiration from structured writing planning and reasoning paths, focusing on reflecting user intentions throughout the writing process. To validate our approach in real-world scenarios, we construct a diverse dataset from unstructured blog posts to benchmark writing performance and introduce a comprehensive evaluation framework assessing the quality of outlines and generated texts. Our evaluations with various LLMs demonstrate that the WritingPath approach significantly enhances text quality according to evaluations by both LLMs and professional writers.
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。
