TEXT2KG-BIKE 2026
LLM-Integrated Knowledge Graph Generation From Text (TEXT2KG) and International BiKE Challenge 2026

Table of Contents

Fifth International Workshop on LLM-Integrated Knowledge Graph Generation From Text (TEXT2KG)

• TEXT2KG Preface
  Summary: There were 18 papers submitted for peer-review to this workshop. Out of these, 12 papers were accepted for this volume, 11 as regular paper and 1 as short papers.

TEXT2KG Short papers

• Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction 1-9
  Luu Huu Phuc, Ratan Bahadur Thapa, Mojtaba Nayyeri, Jingcheng Wu, Evgeny Kharlamov, Steffen Staab

TEXT2KG Regular papers

• From Text to Triples: A Neuro-Symbolic Pipeline for Structured Claim Extraction 10-20
  Massimiliano Fadda, Enrico Motta, Francesco Osborne, Diego Reforgiato Recupero, Angelo Salatino
• Mapping Latent Narrative Content Using LLMs: Essay on Economic Uncertainty Drivers 21-30
  Sami Diaf, Florian Schütze
• CIExMAS: Closed Information Extraction using Multi Agent Systems 31-45
  Max Lautenbach, Sven Hertling
• A Retrieval-Augmented LLM Pipeline for Generating Cognitive Conceptualization Knowledge Graphs 46-64
  Simone Pinna, Silvia Maria Massa, Diego Reforgiato, Daniele Riboni
• xch-MIND: Multi-Agent Interpretive Knowledge Graph Augmentation over Cultural Heritage Linked Data 65-83
  Michele Stingo
• Augmenting Datasets for Fine-Tuning Large Language Models Using Semantic Variations 84-97
  Alexander Chen, Caroline Tang, Jennifer Sleeman
• Using LLMs to Develop Legal Rule Ontologies for Compliance Checking 98-113
  Galileo Sartor, Enrico Francesconi, Adam Wyner
• Integrating LLMs and the PrOntoNarr Ontology for Automated KG Construction in Multi-level Propaganda Narrative Analysis 114-127
  Francesco Orciuoli, Antonella Pascuzzo, Sabrina Senatore
• An Agentic Framework for Dynamic Ontology Generation 128-137
  Ali Amini
• From “Strings” to “Things” for Personal Knowledge Graphs: Evaluating LLM Triple Extraction for Recommendation Systems 138-153
  Abhirup Dasgupta, Fernando Spadea, Oshani Seneviratne
• LLM-Assisted Multilingual Information Extraction for Knowledge Graph Population: The DBpedia Hindi Chapter 154-165
  Sanju Tiwari, Debarghya Datta, Aditya Venkatesh, Ronak Panchal, Ananya, Ronit Banerjee, Tommaso Soru

Third International BiKE Challenge (BiKE 2026)

• BIKE Preface
  Summary: There were 6 papers submitted for peer-review to this Challenge. Out of these, 3 papers were accepted for this volume, 2 as regular paper and 1 as short papers.

BIKE Short papers

• CareWeavers BiKE 2026: BERT-Initialised Graph Embeddings for Natural Product Knowledge Extraction 166-174
  Khyati Patni, Daksh Sammi, Rahul Kharkwal, Diksha Kashyap
• SPHOTA-NEXT: Ontology Enhanced Knowledge Injection for Biochemical Link Prediction 175-180
  Bharath Chand, Thara Prabhakaran, Sanju Tiwari

BIKE Regular paper

• A Multi-Stage Agent Framework with Knowledge Graph Alignment for Natural Product Literature Extraction 181-190
  Shixiong Zhao, Yanming He, Lakshan Karunathilake, Hideaki Takeda