Term & Causal Extraction
Automated reasoning methods for extracting domain-specific terms and causal relations from scientific text, combining symbolic ontologies with neural language models.
Available for research collaboration · Cluj-Napoca, Romania
Grounded reasoning with knowledge graphs and language models.
I'm a PhD student at the Technical University of Cluj-Napoca. My research focuses on term extraction, causal reasoning, and multi-agent platforms that pair structured knowledge with large language models. Applications span biomedical literature, medical chatbots, and nickel-based superalloy design. I'm also a Teaching Assistant for Knowledge-Based Systems, Intelligent Systems, and Artificial Intelligence labs.
Advisor
Prof. Adrian Groza
Currently
Data Scientist @ Digital Science
Research
Knowledge-Graph RAG
Retrieval-augmented generation grounded in structured knowledge graphs, reducing hallucination in medical question-answering systems.
LLMs in Education
Practical adoption of large language models for student assessment generation in engineering education, examining context requirements, fairness, and evaluation.
Multi-Agent Systems
MCP-orchestrated agent pipelines for tasks like automated disinformation detection, where reasoning needs to chain multiple specialized tools.
AI for Scientific Discovery
Multi-agent platforms grounded in structured knowledge graphs for expert-in-the-loop scientific workflows, including nickel-based superalloy design and other materials-informatics tasks.
Publications
Google Scholar ↗2025
-
Reducing Hallucinations in Medical AI: A Knowledge Graph-Augmented Retrieval System for Evidence-Based Age-Related Macular Degeneration Information
IEEE Access Vol. 13, 210624–210639 arXiv:2502.11108 Paper ↗ Preprint ↗ Code ↗
-
MCP-Orchestrated Multi-Agent System for Automated Disinformation Detection
SYNASC 2025 27th Int. Symposium on Symbolic and Numeric Algorithms for Scientific Computing arXiv:2508.10143 Paper ↗ Preprint ↗
-
Leveraging LLMs for Student Assessment Generation in Engineering Education: a Study on Context Requirements and Adoption
EAEEIE 2025 34th Annual Conference, Cluj-Napoca · IEEE Paper ↗ Venue ↗ Code ↗
-
AlloyGraph: A Multi-Agent AI Platform for Nickel-Based Superalloy Design
Under Review ESWA Expert Systems with Applications · Elsevier Code ↗
Demos
Live demo · Materials informatics
AlloyGraph
Multi-agent AI platform for nickel-based superalloy design. Companion to the ESWA submission.
alloygraph.utcluj.ro ↗
Live demo · Medical RAG chatbot
AMD-Chat
Knowledge-graph-augmented retrieval chatbot for evidence-based information on Age-Related Macular Degeneration. Companion to the IEEE Access 2025 paper.
amd-chat.ddns.net ↗
Source code for individual projects lives on GitHub.
Education
-
2022 – Present
Ph.D. in Computer Science
Technical University of Cluj-Napoca
Automated Reasoning and Causality for Term Extraction · Advisor: Prof. Adrian Groza
-
2018 – 2020
M.Sc. in Artificial Intelligence
Technical University of Cluj-Napoca
Early Warning System for Predictive Maintenance in Optical Inspection
-
2014 – 2018
B.Sc. in Computer Science
Technical University of Cluj-Napoca
Steering Support in Electrical Power Steering
Experience
-
2022 – Present
Data Scientist
-
2017 – 2022
Data Scientist / Software Engineer