RAGE-KG 2025: Retrieval-Augmented Generation Enabled by Knowledge Graphs ISWC Nara, Japan, November 2-3, 2025

RAGE-KG (Retrieval-Augmented Generation Enabled by Knowledge Graphs) is an established academic workshop on synergies between Knowledge Graphs, Retrieval-Augmented Generation and Large Language Models, coming to ISWC 2025 in Nara, Japan.

The workshop explores the state of the art and goes beyond in integrating Retrieval-Augmented Generation (RAG) with Knowledge Graphs as well as the synergies between Large Language Models and the Linked Open Data ecosystem. We aim to foster innovative RAG architectures relying on Semantic Web standards and new approaches to make Linked Open Data usable by LLMs, enhancing their ability to generate reliable, verifiable and context-aware responses based on structured, decentralized and authoritative data sources.

Call for Papers: 2025.rage-kg.org

Workshop pages on social media (publishing updates):

• Connect on Bluesky: @rage-kg.bsky.social
• Connect on Mastodon: mastodon.social/@ragekg
• Follow the LinkedIn page: linkedin.com/company/rage-kg

Submission Guidelines

All papers must be original and not simultaneously submitted to another journal or conference. The following paper categories are welcome:

• Full Papers:  
  • Novel research contributions of extended length
  • Related to workshop topics (below)
  • 7-12 pages excluding references
  • Papers should follow the 1-column CEUR format (https://ceur-ws.org/HOWTOSUBMIT.html#CEURART)
• Short Papers: 
  • Novel research contributions and preliminary results
  • Related to workshop topics (below)
  • 4-6 pages excluding references
  • Papers should follow the 1-column CEUR format (https://ceur-ws.org/HOWTOSUBMIT.html#CEURART)
• AI-Generated Papers: 
  • Papers generated using AI
  • Upload a description of the generation approach (1-2 pages) and the generated paper itself (distinct paper sections are also allowed)
    • Approach Description: Include an explanation of your method for generating the paper. The length can vary from a brief overview of two paragraphs to a more detailed description of up to two pages. The description should follow the 1-column CEUR format (https://ceur-ws.org/HOWTOSUBMIT.html#CEURART).
    • AI-Generated Paper: Submit a paper generated by AI on a topic of your choosing. The AI-generated paper can be in any format and follow any template.
  • We hope this initiative will provide valuable insights into the role of AI in (the future of) research, and we look forward to your potential contribution.

List of Topics

• RAG architectures leveraging KGs, Semantic Web standards and LOD
• Training and fine-tuning LLMs with structured data
• Prompting Language Models with structured data
• Evaluating RAG architectures with structured data
• RAG design patterns including GraphRAG and Agentic RAG
• Language Model and ontology-supported SPARQL query generation
• Neurosymbolic approaches for integrating Language Models with LOD
• Use Cases, Work-In-Progress and *Bold Proposals* for RAG systems

Organizing Committee

• Daniil Dobriy (Institute for Data, Process and Knowledge Management, WU Vienna, Austria)
• Sanju Tiwari (TIB Hannover, Germany & Sharda University, Greater Noida, India)
• Jennifer D’Souza (TIB Leibniz Information Centre for Science and Technology, Hannover, Germany)
• Nandana Mihindukulasooriya (IBM Research, New York, USA)
• Francesco Osborne (The Open University, Milton Keynes, United Kingdom)

Publication

RAGE-KG 2025 proceedings will be published with CEUR (https://ceur-ws.org/).

Venue

The conference will be co-located with ISWC 2025 (24th International Semantic Web Conference) and held in Nara, Japan.

Contact

All questions about submissions should be emailed to daniil.dobriy@wu.ac.at.

Detailed information on the Call for Papers is available on the website: 2025.rage-kg.org