Hierarchical Memory Organization for Wikipedia Generation

TL;DR

This paper presents MOG, a hierarchical memory framework for autonomous Wikipedia article generation that improves informativeness, verifiability, and traceability by organizing web-derived information into a structured memory system.

Contribution

Introduces a novel hierarchical memory architecture and citation module for more accurate and reliable Wikipedia article generation.

Findings

MOG outperforms baseline methods on the WikiStart dataset.

Hierarchical memory improves alignment with article outlines.

Citation module enhances traceability of generated content.

Abstract

Generating Wikipedia articles autonomously is a challenging task requiring the integration of accurate, comprehensive, and well-structured information from diverse sources. This paper introduces the Memory Organization-based Generation (MOG) framework, a novel approach to address these challenges by leveraging a hierarchical memory architecture. MOG extracts fine-grained memory units from web documents, recursively organizes them into a Wikipedia-style hierarchical structure, and uses this structure to guide the generation process. This ensures alignment between memory and the article outline, improving both informativeness and verifiability while minimizing hallucinations. Additionally, a citation module is implemented to enhance traceability by linking every generated sentence to specific memory units. Evaluations on our newly created WikiStart dataset demonstrate that MOG outperforms baseline methods in producing informative and reliable articles, making it particularly robust in real-world scenarios.