Hierarchical Memory Organization for Wikipedia Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916816865984512 |
|---|---|
| author | Yu, Eugene J. Zhu, Dawei Song, Yifan Wong, Xiangyu Zhang, Jiebin Shi, Wenxuan Li, Xiaoguang Liu, Qun Li, Sujian |
| author_facet | Yu, Eugene J. Zhu, Dawei Song, Yifan Wong, Xiangyu Zhang, Jiebin Shi, Wenxuan Li, Xiaoguang Liu, Qun Li, Sujian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_23393 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | 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 Computation and Language 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. |
| title | Hierarchical Memory Organization for Wikipedia Generation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2506.23393 |