Knowledge pull requests improve continual document updates across languages
Knowledge Pull Requests for Continual Document Authoring
Computation and Language
Summary
Documents like Wikipedia articles need constant updates as new facts appear. The authors present a method called Knowledge Pull Requests (KPRs) that helps update documents by clearly showing what knowledge changes and how the text is altered. KPRs work by extracting new claims, deciding where they fit in the document, and marking contradictions with old content. This approach preserves more existing information and adds more useful facts than rewriting entire texts from scratch. It also helps answer questions better by including knowledge from documents in different languages.
What this means in practice
- •For content management teams: Integrate and track knowledge updates continually in multilingual documentation to improve accuracy and transparency of changes.
- •For knowledge base developers: Enhance automated updates of query-driven reports by selectively adding new information while preserving existing verified content.
Authors
Alexander Martin, Benjamin Van Durme
Abstract
We introduce Knowledge Pull Requests (KPRs), a framework for continual document authoring that makes each change interpretable. Documents require ongoing revision as new knowledge surfaces from other sources, languages, or times, but existing approaches either edit with no account of what knowledge changed or regenerate from scratch. A KPR integrates new knowledge into a document by extracting claims, filtering and routing them to sections, and flagging conflicts with existing content, producing a ChangeLog that separates what knowledge changes (claim proposal) from how the text changes (document diff). We evaluate KPRs on revising Wikipedia across languages and updating query-driven reports on RAGTIME. KPRs integrate more information and better preserve existing content than rewriting from sources or regenerating from scratch, while adding the most information per token generated. A KPR-revised article also grounds question answering better than a frontier model with search, which does not surface knowledge documented only in other languages.