DeepMind Blog

Making it easier to understand how content was created and edited

Read the original on DeepMind Blog →

We're expanding our tools to help you understand how content was created and edited across the web.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at DeepMind Blog.

arXiv Computation and Language
Sep 23

Knowledge Pull Requests for Continual Document Authoring

The paper introduces Knowledge Pull Requests (KPRs), a framework that enables continual document authoring by making each change interpretable. KPRs extract claims from new knowledge sources, filter and route them to appropriate sections, and flag conflicts with existing content, producing a ChangeLog that separates knowledge changes from textual edits. Experiments on revising Wikipedia and updating query-driven reports show that KPRs integrate more information, better preserve existing content, and improve question answering performance compared to rewriting from scratch or using frontier models with search.

By Alexander Martin, Benjamin Van Durme
arXiv AI
Sep 12

From Queries to Narratives: Cultural Heritage Data Stories for Knowledge Graph Exploration and Quality Assessment

The paper introduces data stories as narrative documents that combine explanatory text, images, and executable SPARQL queries with visualized results to make cultural‑heritage knowledge graphs more accessible. It describes how these stories guide users through unfamiliar graphs, create reproducible narratives, and uncover hidden data‑quality issues. The authors present LODEON, an authoring platform with Sparnatural and AI‑assisted tools, and report early positive feedback from seminars and workshops.

By Tabea Tietz, Torsten Schrade, Etienne Posthumus, Linnaea S\"ohn, Jonatan Jalle Steller, J\"org Waitelonis, Harald Sack