About me

I am a Senior Data Scientist at Fraunhofer IAIS and a Research Fellow at the Applied Machine Learning Lab at the University of Bonn. My work sits at the intersection of Machine Learning and NLP, with a focus on building LLM-based Agent Systems and context-aware Recommender Systems for applications in Finance and Healthcare.

I submitted my PhD thesis in Computer Science at the University of Bonn at the start of 2026, with a dissertation titled Context-Aware Foundational Models for Cross-Domain Recommender Systems. My research explores informed Recommender Systems and Model Distillation in the context of Large Language Models, bridging academic research with production-grade industry applications.

Before my current role, I held Data Scientist and Senior Data Scientist positions at Fraunhofer IAIS, where I architected and deployed LLM-based Agent Systems for enterprise clients across Finance and Healthcare. Prior to that, I gained industry experience as an intern at KPMG in Deal Advisory & Analytics and at Porsche Consulting.

Research Interests

• LLM-based Agent Systems: Designing and deploying autonomous LLM agents for complex workflows.

• Recommender Systems: Developing context-aware, cross-domain recommendation models with a focus on personalized medicine and financial auditing.

• Model Distillation: Investigating knowledge distillation techniques to build resource-efficient Foundational Models for specialized domains.

Highlighted Publications

Google Scholar

• Benchmark Success, Clinical Failure: When Reinforcement Learning Optimizes for Benchmarks, Not Patients Armin Berger*, Manuela Bergau*, Helen Schneider, Saad Ahmad, Thomas Anglim Lagones, David Berghaus, Tobias Deußer, Gianluca Brugnara, Martha Foltyn-Dumitru, Korbinian Schlamp, Philipp Vollmuth, Rafet Sifa arXiv preprint arXiv:2512.23090, 2025. Submitted to IJCNN 2026. [arXiv]

• Reasoning LLMs in the Medical Domain: A Literature Survey Armin Berger*, Sarthak Khanna*, David Berghaus, Rafet Sifa Proc. IEEE DSAA, 2025

• Optimizing Rare Disease Patient Matching with Large Language Models Armin Berger*, Ali Hamza Bashir*, David Berghaus*, Afsan Nazia Mowmita, Lorenz Grigull, Lara Fendrich, Henriette Högl, Gundula Ernst, Ralf Schmidt, David Bascom, Tom Anglim Lagones, Tobias Deußer, Thiago Bell Felix de Oliveira, Max Lübbering, Rafet Sifa Proc. IEEE BigData, 2024

• Advancing Personalized Medicine: A Scalable LLM-based Recommender System for Patient Matching Armin Berger*, David Berghaus*, Ali Hamza Bashir, Lorenz Grigull, Lara Fendrich, Tom Anglim Lagones, Henriette Högl, Gundula Ernst, Ralf Schmidt, David Bascom, Tobias Deußer, Thiago Bell Felix de Oliveira, Max Lübbering, Rafet Sifa Proc. IEEE BigData, 2024

• Tackling Data Sparsity and Combinatorial Challenges in Rare Disease Matching with Medical Informed Machine Learning Armin Berger, Tom Anglim Lagones, Lorenz Grigull, Lara Fendrich, Thiago Bell Felix de Oliveira, Henriette Högl, Gundula Ernst, Ralf Schmidt, David Bascom, Tobias Deußer, Max Lübbering, Rafet Sifa Proc. IEEE BigData, 2024

• Advancing Risk and Quality Assurance: A RAG Chatbot for Improved Regulatory Compliance Lars Hillebrand*, Armin Berger*, Daniel Uedelhoven, David Berghaus, Ulrich Warning, Tim Dilmaghani, Bernd Kliem, Thomas Schmid, Rüdiger Loitz, Rafet Sifa Proc. IEEE BigData, 2024

• Towards Automated Regulatory Compliance Verification in Financial Auditing with Large Language Models Armin Berger*, Lars Hillebrand*, David Leonhard, Tobias Deußer, Thiago Bell Felix de Oliveira, Tim Dilmaghani, Mohamed Khaled, Bernd Kliem, Rüdiger Loitz, Christian Bauckhage, Rafet Sifa Proc. IEEE BigData, 2023 [DOI]

• Improving Zero-Shot Text Matching for Financial Auditing with Large Language Models Lars Hillebrand*, Armin Berger*, Tobias Deußer, Tim Dilmaghani, Mohamed Khaled, Bernd Kliem, Rüdiger Loitz, Maren Pielka, David Leonhard, Christian Bauckhage, Rafet Sifa Proc. ACM DocEng, 2023 [DOI]

Contact Details

If you want to get in contact, write an Email to aberger[at]uni-bonn.de. You can also swing by my office in Room 2.109, Friedrich-Hirzebruch-Allee 8, 53115 Bonn.