Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models

TL;DR

WritingPath is a framework that guides large language models using explicit outlines to produce high-quality, goal-oriented texts aligned with user intentions, improving content creation in real-world scenarios.

Contribution

It introduces a novel outline-guided approach for LLMs, incorporating structured planning and reasoning to enhance writing quality and user alignment.

Findings

WritingPath significantly improves text quality according to evaluations.

The framework effectively reflects user intentions in generated content.

Benchmarking with diverse datasets validates the approach's effectiveness.

Abstract

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.