Head of the Research Group: Dr. Gergely LUKÁCS
Members of the Research Group: Kornél GÁTMEZEI, Tamás Béla KIS, Dr. Zoltán MÁTHÉ
Contact: lukacs@itk.ppke.hu
Our research group conducts application-driven research in data-intensive systems and artificial intelligence, combining technical expertise with a strong focus on real-world impact.
Our data engineering research covers relational, distributed, time-series, unstructured, and vector databases, with an emphasis on system design, applications, performance benchmarking, and emerging technologies.
In machine learning, we focus on structured data analytics and large language models (LLMs). Building on extensive experience in benchmarking database and big data systems, our current research investigates the evaluation of generative AI, including retrieval-augmented generation (RAG), LLM-as-a-Judge, vector embeddings, data anonymization, and text-to-SQL.
Our interdisciplinary research addresses societal challenges, particularly environmental sustainability and the strengthening of human relationships and communities. Our work includes industry quality integrated environmental and water management information systems, the development and evaluation of voice-based social media platforms, social network analysis in hospital chaplaincy communities, and the assessment of LLM-generated responses to interpersonal and relationship-related questions.
Impact of anonymization on vector embeddings in ITOps data, measured by changes in embedding-based similarity metrics. Kornél Gátmezei, RAG-Enhanced LLMs and Their Evaluation, Master’s Thesis, 2026.
Future research directions, collaboration opportunities
We welcome research, industrial, and interdisciplinary collaborations in data engineering, artificial intelligence, and AI evaluation. We support industry-driven student projects, provide expert consulting, and seek partnerships with social scientists to explore the impact of digitalization and AI on human relationships and communities.
Key publications
- Yang, Z. Gy., Stajer, L. A., Lukács, G. (2025). Under the hood: An inside look at PULI models In: Tómács, Tibor (szerk.) PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON FORMAL METHODS AND FOUNDATIONS OF ARTIFICIAL INTELLIGENCE EGER, MAGYA-RORSZÁG: ESZTERHÁZY KÁROLY KATOLIKUS EGYETEM LÍCEUM KIADÓ
- Horváth, A., Oláh, A., Pintér, A., Siklósi, B., Lukács, G., Reguly, I. Z., Tornai, K., Zsedrovits, T., Máthé, Z. (2025). Anomaly Detection Algorithms for Real-Time Log Data Analysis at Scale. IEEE ACCESS 13 pp. 136288-136311, 24 p.
- Lukács, G., Jani, M. (2016). Analyzing speech and music blocks in radio channels: Lessons learned for playlist generation. IN: ROBLES, R; TALLON-BALLESTEROS, A J; PIT, PICHAPPAN (SZERK.) ELEVENTH INTERNATIONAL CONFERENCE ON DIGITAL INFORMATION MANAGEMENT (ICDIM) NEW YORK, AMERIKAI EGYESÜLT ÁLLAMOK: INSTITUTE OF ELECTRICAL AND ELECTRONICS ENGINEERS (IEEE)
Selected Theses Supervised within the Research Group (View the full list)
- Kornél GÁTMEZEI (2026): Retrieval-Augmented Generation (RAG)-Enhanced Large Language Models and Their Evaluation
- Réka GYERTYÁS (2026): Evaluation of Embedding Methods (BSc thesis)
- Benedek György NAVRATYIL (2026): Benchmarking Large Language Models (BSc thesis)
- Dániel PÁSZTOR (2026): Horizontal Scaling of Data Processing and Machine Learning Algorithms (MSc thesis)
- Zita RADVÁNYI (2026): Benchmarking Vector Databases (BSc thesis)
- Klaudia SZILI (2026): Social Media Data Analysis Using Advanced Visualization and Machine Learning Methods (MSc thesis)
- Levente LINCZENBOLD (2025): Benchmarking Generative AI on Marriage and Family-Related Topics (Postgraduate thesis)
- András SZENTENDREY (2025): Scalable Data Processing with Python (BSc thesis)
- Lilla BÉKÉSI (2024): AI-Assisted Data Analysis (Postgraduate thesis)
- Béla BIFKOVICS (2019): Scalable Data Processing with Apache Spark (BSc thesis)
