Hierarchical Memory Organization for Wikipedia Generation
Yu, Eugene J., Zhu, Dawei, Song, Yifan, Wong, Xiangyu, Zhang, Jiebin, Shi, Wenxuan, Li, Xiaoguang, Liu, Qun, Li, Sujian
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Jul-1-2025
- Country:
- Asia
- Japan > Honshū
- Kantō > Tokyo Metropolis Prefecture > Tokyo (0.04)
- Brunei (0.04)
- Cambodia
- Kampot Province (0.04)
- Phnom Penh Province > Phnom Penh (0.05)
- Preah Sihanouk Province > Sihanoukville (0.04)
- Siem Reap Province > Siem Reap (0.05)
- Malaysia (0.14)
- Vietnam (0.05)
- Laos (0.04)
- Philippines (0.15)
- Timor-Leste (0.04)
- China > Beijing
- Beijing (0.04)
- Southeast Asia (0.04)
- Thailand > Bangkok
- Bangkok (0.04)
- Singapore (0.06)
- Myanmar > Tanintharyi Region
- Dawei (0.04)
- Indonesia > Java
- Japan > Honshū
- Europe > Ireland
- Leinster > County Dublin > Dublin (0.04)
- North America > Mexico
- Mexico City > Mexico City (0.04)
- Asia
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Consumer Products & Services > Travel (0.68)
- Leisure & Entertainment > Sports
- Olympic Games (0.68)
- Technology: