RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery
This addresses the challenge of automated long-text generation for applications like encyclopedia creation, though it appears incremental as it builds on existing retrieval-augmented methods.
The paper tackled the problem of generating knowledge-intensive long texts like encyclopedia articles by proposing RAPID, a retrieval-augmented framework that significantly outperformed state-of-the-art methods on metrics such as long-text generation, outline quality, and latency.
Generating knowledge-intensive and comprehensive long texts, such as encyclopedia articles, remains significant challenges for Large Language Models. It requires not only the precise integration of facts but also the maintenance of thematic coherence throughout the article. Existing methods, such as direct generation and multi-agent discussion, often struggle with issues like hallucinations, topic incoherence, and significant latency. To address these challenges, we propose RAPID, an efficient retrieval-augmented long text generation framework. RAPID consists of three main modules: (1) Retrieval-augmented preliminary outline generation to reduce hallucinations, (2) Attribute-constrained search for efficient information discovery, (3) Plan-guided article generation for enhanced coherence. Extensive experiments on our newly compiled benchmark dataset, FreshWiki-2024, demonstrate that RAPID significantly outperforms state-of-the-art methods across a wide range of evaluation metrics (e.g. long-text generation, outline quality, latency, etc). Our work provides a robust and efficient solution to the challenges of automated long-text generation.