RAGE-KG 2025
Retrieval-Augmented Generation Enabled by Knowledge Graphs 2025

Table of Contents

• Preface
  Summary: There were 21 papers submitted for peer-review to the workshop. Out of these, 15 papers were accepted for inclusion in the proceedings.

• HubLink: A Novel Question Answering Retrieval Approach over Knowledge Graphs (regular paper) 1-18
  Angelika Kaplan, Jan Keim, Marco Schneider, Ralf Reussner
• Learning to Refine: An Agentic RL Approach for Iterative SPARQL Query Construction (regular paper) 19-32
  Floris Vossebeld, Shenghui Wang
• RETROFIT-CQ Revisited: Leveraging Ontology Triples and Context in Few-Shot LLM Prompting (regular paper) 33-44
  Meiqing Li, Reham Alharbi, Jacopo de Berardinis, Valentina Tamma, Terry R. Payne
• HyP-KGRAG: Hypothetical Path-Based Knowledge Graph Retrieval Augmented Generation with DeepSeek (regular paper) 45-55
  Zhaotai Liu, Harald Sack, Genet Asefa Gesese
• RecipeRAG: A Knowledge Graph-Driven Approach to Personalized Recipe Retrieval and Generation (regular paper) 56-68
  Julie Loesch, Emin Durmuş, Remzi Celebi
• Benchmarking KG-based RAG Systems: A Case Study of Legal Documents (regular paper) 69-82
  Jaycent G. Ongris, Fariz Darari, Berty C. L. Tobing, Douglas R. Faisal, On Lee
• Beyond the Metrics: An Investigation into the Reliability of Evaluation Metrics for Domain Specific Graph-based Question Answering (regular paper) 83-96
  Lia Draetta, Marco Antonio Stranisci, Flaviana Corallo, Pier Felice Balestrucci, Michael Oliverio, Rossana Damiano, Alessandro Mazzei
• Parallel and Multi-Stage Knowledge Graph Retrieval for Behaviorally Aligned Financial Asset Recommendations (regular paper) 97-106
  Fernando Spadea, Oshani Seneviratne
• From Speech to Semantics: Enabling Conversational Access to Scholarly Knowledge Graph (regular paper) 107-119
  Umair Ahmed, Andrea Polini, Nicolas Ferranti
• Beyond Statistical Parroting: Hard-Coding Truth into LLMs via Ontologies (regular paper) 120-131
  Hamed Babaei Giglou, Simon Burbach, Francesco Compagno, Muhammad Ismail, Gunjan Singh, Sebastian Rudolph
• AgCyRAG: an Agentic Knowledge Graph based RAG Framework for Automated Security Analysis (regular paper) 132-144
  Kabul Kurniawan, Rayhan Firdaus Ardian, Elmar Kiesling, Andreas Ekelhart
• Chunk-Link: Context-aware Chunk Completion (short paper) 145-152
  Kenichirou Narita, Satoshi Munakata
• User Interface and Agent Interface for Online Generation of Knowledge Graph’s Competency Questions and Question-Query Training Sets (short paper) 153-159
  Yousouf Taghzouti, Franck Michel, Tao Jiang, Louis-Felix Nothias, Fabien Gandon
• Boosting Knowledge Graph Question Answering with Open Source Lightweight Large Language Models and RAG Techniques (short paper) 160-168
  Mario Caruso, Giorgia Lodi, Carlo Macis, Simone Persiani, Valentina Presutti
• Towards Harmonised Rail Safety Knowledge: LLM Techniques for EU Accident Report Processing (short paper) 169-174
  Shahrom Sohi, Dragomir Balan, Amin Anjomshoaa, Axel Polleres