Hierarchical Memory Organization for Wikipedia Generation
This addresses the challenge of generating accurate and structured Wikipedia articles from diverse sources, which is an incremental improvement in natural language generation for knowledge-intensive tasks.
The paper tackled the problem of autonomously generating Wikipedia articles by introducing the Memory Organization-based Generation (MOG) framework, which uses a hierarchical memory architecture to improve informativeness and verifiability, and it outperformed baseline methods on the WikiStart dataset.
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.