Submissions:2025/Automatic Wikipedia Updating with LLM Agents

From WikiConference North America
Jump to navigation Jump to search

This submission has been noted and is pending review for WikiConference North America 2025.



Title:

Automatic Wikipedia Updating with LLM Agents

Type of session:

Lecture (15-30 min)

Session theme(s):

Future of Wikipedia

Abstract:

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. This talk introduces 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 the system's ability to identify and suggest timely factual updates. This opens up a promising research direction in LLM agents for suggesting Wikipedia updates with human editors in the loop.

Author name(s):

Revanth Gangi Reddy, Tanay Dixit, Jiaxin Qin, Cheng Qian, Daniel Lee, Jiawei Han, Kevin Small, Xing Fan, Ruhi Sarikaya, Heng Ji

Wikimedia username(s):

Affiliated organization(s):

University of Illinois at Urbana Champaign

Estimated length of session

20 mins

Will you be presenting remotely?

I will present in-person

Okay to livestream?

Livestreaming is okay

Previously presented?

Special requests: