WINELL: Wikipedia Never-Ending Updating with LLM Agents

TL;DR

WiNELL introduces a multi-agent framework leveraging LLMs to continuously update Wikipedia articles by aggregating online info, selecting key knowledge, and generating edit suggestions for human review, improving update timeliness and accuracy.

Contribution

The paper presents WiNELL, a novel LLM-based multi-agent system for automatic, continuous Wikipedia content updating, outperforming existing models in coverage and efficiency.

Findings

Outperforms open-source and GPT-4o models in coverage and efficiency.

Successfully identifies and suggests timely factual updates on high-activity pages.

Demonstrates potential for automatic, never-ending knowledge base maintenance.

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. 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.