Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2508.03728 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908479673860096 |
|---|---|
| author | Reddy, Revanth Gangi Dixit, Tanay Qin, Jiaxin Qian, Cheng Lee, Daniel Han, Jiawei Small, Kevin Fan, Xing Sarikaya, Ruhi Ji, Heng |
| author_facet | Reddy, Revanth Gangi Dixit, Tanay Qin, Jiaxin Qian, Cheng Lee, Daniel Han, Jiawei Small, Kevin Fan, Xing Sarikaya, Ruhi Ji, Heng |
| contents | Wikipedia, a vast and continuously consulted knowledge base, faces significant challenges in maintaining up-to-date content due to its reliance on manual human editors. Inspired by the vision of continuous knowledge acquisition in NELL and fueled by advances in LLM-based agents, this paper introduces WiNELL, an agentic framework for continuously updating Wikipedia articles. Our approach employs a multi-agent framework to aggregate online information, select new and important knowledge for a target entity in Wikipedia, and then generate precise edit suggestions for human review. Our fine-grained editing models, trained on Wikipedia's extensive history of human edits, enable incorporating updates in a manner consistent with human editing behavior. Our editor models outperform both open-source instruction-following baselines and closed-source LLMs (e.g., GPT-4o) in key information coverage and editing efficiency. End-to-end evaluation on high-activity Wikipedia pages demonstrates WiNELL's ability to identify and suggest timely factual updates. This opens up a promising research direction in LLM agents for automatically updating knowledge bases in a never-ending fashion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03728 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WINELL: Wikipedia Never-Ending Updating with LLM Agents Reddy, Revanth Gangi Dixit, Tanay Qin, Jiaxin Qian, Cheng Lee, Daniel Han, Jiawei Small, Kevin Fan, Xing Sarikaya, Ruhi Ji, Heng Computation and Language Wikipedia, a vast and continuously consulted knowledge base, faces significant challenges in maintaining up-to-date content due to its reliance on manual human editors. Inspired by the vision of continuous knowledge acquisition in NELL and fueled by advances in LLM-based agents, this paper introduces WiNELL, an agentic framework for continuously updating Wikipedia articles. Our approach employs a multi-agent framework to aggregate online information, select new and important knowledge for a target entity in Wikipedia, and then generate precise edit suggestions for human review. Our fine-grained editing models, trained on Wikipedia's extensive history of human edits, enable incorporating updates in a manner consistent with human editing behavior. Our editor models outperform both open-source instruction-following baselines and closed-source LLMs (e.g., GPT-4o) in key information coverage and editing efficiency. End-to-end evaluation on high-activity Wikipedia pages demonstrates WiNELL's ability to identify and suggest timely factual updates. This opens up a promising research direction in LLM agents for automatically updating knowledge bases in a never-ending fashion. |
| title | WINELL: Wikipedia Never-Ending Updating with LLM Agents |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2508.03728 |