Research Scientist working on Semantic Web, Knowledge Graphs, Neuro-Symbolic AI, Large Language Models, Continual Learning, Retrieval-Augmented Generation, and Trustworthy AI.
I am a Research Scientist at Senckenberg – Leibniz Institution for Biodiversity and Earth System Research and a PhD researcher in Computer Science at Free University of Berlin. My work focuses on scalable and explainable methods for knowledge graph construction, completion, reasoning, and information extraction by combining symbolic reasoning with foundation models. I am particularly interested in applying these methods to scientific knowledge management and biodiversity knowledge integration.
Selected research and infrastructure projects from recent academic and applied work.
PhD research on continual relation extraction using transformers, encoder-decoder models, and large language models to improve knowledge graph completeness with explainable and continually learning methods.
Developing knowledge graph and LLM-based approaches for semantic integration, entity resolution, and biodiversity knowledge modeling within large-scale scientific data infrastructures.
Developing neuro-symbolic methods for continual relation extraction and hallucination resolution with SHACL-based explainability for trustworthy knowledge graph construction.
Investigating LLM-based approaches for continual relation extraction to improve adaptive knowledge graph completion across evolving scientific domains.
Building retrieval-augmented generation workflows for relation extraction that combine external evidence with more reliable structured prediction.
Advancing ontology matching with graph representation learning methods for alignment discovery across heterogeneous knowledge organization systems.
Selected education, experience, skills, and academic service from the current CV.
Selected recent publications and submissions from the CV.
IEEE Access journal
Semantic Web Journal
ACL 2025 XLLM Workshop Paper.
Semantics 2024
International Workshop on Ontology Matching, ISWC 2022.
Recent milestones from research, infrastructure, and academic service.
I will speak in SYM46 on AI-Readiness Metrics and Metadata for Biodiversity Data.
Working on knowledge graph and LLM-based approaches for semantic integration, entity resolution, and biodiversity knowledge modeling.
Received high-performance computing support to scale deep learning models and large-scale text-extraction workflows.
Serving the community through peer review and editorial activities in Semantic Web research.
The core iteration of this work was also accepted and presented at the Wikidata Workshop at ISWC 2023.
For research collaborations, publications, and project updates, please get in touch by email or follow my work online.