RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gu, Hongchao, Li, Dexun, Dong, Kuicai, Zhang, Hao, Lv, Hang, Wang, Hao, Lian, Defu, Liu, Yong, Chen, Enhong
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929738500538368
author Gu, Hongchao
Li, Dexun
Dong, Kuicai
Zhang, Hao
Lv, Hang
Wang, Hao
Lian, Defu
Liu, Yong
Chen, Enhong
author_facet Gu, Hongchao
Li, Dexun
Dong, Kuicai
Zhang, Hao
Lv, Hang
Wang, Hao
Lian, Defu
Liu, Yong
Chen, Enhong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_00751
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery
Gu, Hongchao
Li, Dexun
Dong, Kuicai
Zhang, Hao
Lv, Hang
Wang, Hao
Lian, Defu
Liu, Yong
Chen, Enhong
Computation and Language
Artificial Intelligence
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.
title RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2503.00751