Christian Nickel

Christian Nickel

Computer Scientist and Researcher @ RC-Trust. Exploring AI-Reasoning, -Safety, -Security and its intersection with Human Behavior. Passionate about both progress and safety in the agentic age, incorporating multidisciplinary approaches to push the boundaries of AI and its applications.

Christian Nickel - CV

Also see: LinkedIn

Research Interests

→ Full details on the Interests page

  • Generative AI, LLMs, NLP, Deep Learning
  • AI-Safety and (Cyber-)Security
    • Model Reasoning, Alignment and Steerability
    • Tool Usage, and Agentic AI Systems
  • Trustworthy Machine Learning
  • Human–AI Interaction (HAI), Usable Security, and HCI — including Theory of Mind and user modeling
  • Decentralized, local and privacy-preserving AI deployments
  • Distributed Ledger Technology (DLT), Self-Sovereign Identity (SSI) and Smart Contracts

Professional Experience

  • PhD Researcher — Jan 2025 – present
    • Research Center Trustworthy Data Science and Security (RC-Trust) & University of Duisburg-Essen — Group: Human Understanding of Algorithms and Machines (HUAM), Prof. Dr. Nils Köbis
    • Investigating shifts in human strategic behavior in economic games when facing AI opponents
    • Research at the intersection of AI, behavioral science, and human cognition
    • Parallel project on LLM agent steerability and behavior analysis (with Dr. Florian Mai, University of Bonn)
  • Researcher — Oct 2024 – Dec 2024
    • Data Science & Language Technologies Group (CAISA Lab), Bonn-Aachen International Center for Information Technology (b-it), University of Bonn
    • Built and evaluated socially-aware LLM-based multi-agent systems incorporating Theory of Mind
    • Investigated emergent Theory of Mind capabilities in Large Language Models
    • Published research on LLM Theory of Mind robustness (WiNLP @ EMNLP 2024, Best Poster Award · OpenReview)
    • Presented follow-up work at the ToM4AI Workshop @ AAAI 2025 (PDF, OpenReview)
  • Research Assistant — Sep 2022 – Aug 2023
    • Fraunhofer Institute for Applied Information Technology (FIT)
    • Developed and evaluated Self-Sovereign Identity (SSI) solutions with a focus on usability and interoperability
    • Worked on Distributed Ledger Technology (DLT/Blockchain) projects
  • Teaching Assistant — Apr 2021 – Sep 2021 & Apr 2022 – Sep 2022
    • University of Bonn, Department of Computer Science
    • Tutored and held lectures in the “Human-Computer Interaction” course under Prof. Dr. Matthew Smith and Dr. Christian Tiefenau
  • Teaching Assistant — Oct 2020 – Mar 2021
    • University of Bonn, Department of Computer Science
    • Tutored “Datenzentrierte Informatik” (Data-Centric Computer Science), a course on Machine Learning and Databases under Prof. Dr. Christian Bauckhage

Education

  • M.Sc. in Computer Science — Jul 2021 – Sep 2024
    • University of Bonn — Focus: Artificial Intelligence, Machine Learning, Cybersecurity
  • B.Sc. in Computer Science (Psychology minor) — Oct 2017 – Jul 2021
    • University of Bonn — Focus: Cybersecurity, Usable Security, Artificial Intelligence

Awards & Recognition

  • Best Poster Award — 2024
    • WiNLP @ EMNLP 2024, Miami, FL, USA — “Probing the Robustness of Theory of Mind in Large Language Models” — with Laura Schrewe
    • Large Language Models fail to attribute beliefs to others in non-trivial situations; Chain-of-Thought reasoning seldom helps.

Publications & Presentations

→ Full details on the publications page

Projects

  • Socially-Aware LLM Agents with Theory of Mind — 2024
    • Data Science & Language Technologies Group (CAISA Lab), Bonn-Aachen International Center for Information Technology (b-it), University of Bonn
    • Developed framework for LLM-based social agents with authentic personality representation and Theory of Mind reasoning
    • Implemented system for agents to maintain private mental states and public conversational outputs
    • Generated persona-driven conversations using personality vectors (Big5, MBTI)
    • Created evaluation framework for personality authenticity
    • Led bi-weekly Special Interest Group on social agents in 2024
  • Theory of Mind in Large Language Models — 2024
    • Data Science & Language Technologies Group (CAISA Lab), Bonn-Aachen International Center for Information Technology (b-it), University of Bonn
    • Developed comprehensive human-written and annotated benchmark for evaluating ToM in LLMs
    • Created novel metrics for assessing Chain-of-Thought reasoning correctness
    • Investigated robustness of ToM capabilities under various perturbations
    • Presented at WiNLP @ EMNLP 2024
  • Human vs Machine Attention Analysis — 2023
    • Lab: Development and Application of Data Mining, University of Bonn
    • Compared human eye-tracking data with machine attention mechanisms in NLP
    • Analyzed correlation between human fixation patterns and machine saliency scores
    • Evaluated differences between English and German language processing
  • Ethics in Autonomous Weapon Systems — 2023
    • AI Ethics Seminar, University of Bonn
    • Analyzed ethical implications and legal framework of autonomous weapons systems
    • Evaluated concepts of meaningful human control in military AI applications
  • Privacy Analysis of IoT Devices — 2021
    • Bachelor Thesis, University of Bonn
    • Developed methodology for analyzing privacy compliance of IoT devices
    • Conducted comparative analysis of smart cameras from different jurisdictions
    • Implemented network traffic analysis setup using Raspberry Pi
    • Created evaluation framework based on GDPR requirements
  • RansomDenied: Usable Ransomware-Resistant Backup System — 2020
    • Bachelor Lab Project, University of Bonn
    • Designed and implemented user-friendly backup system resistant to ransomware attacks
    • Conducted user research including expert interviews and requirements analysis
    • Applied user-centered design principles to a security-critical application
  • ReselMusic: Cloud-based Multi-User Social Playlist Service — 2014
    • Private Project
    • Designed and implemented cloud service for multimedia aggregation in playlists
    • PartyMode: users could check in via QR code and contribute to the playlist

Professional Development & Trainings

  • Trade Secrets Act (GeschGehG) — PROvendis GmbH, Jun 2024
  • PhD Workshop: “Promovieren?! Ja oder Nein?” — Bonn Graduate Center, May 2024
  • Voice Training: “Starke Stimme” — Voice Coach Anne Weller, May 2024
  • Software Copyright Protection — PROvendis GmbH, Apr 2024
  • Business Administration Fundamentals — University of Cologne, Oct 2016 – Mar 2017
  • Business Start-up Training — University of Cologne, Oct 2015 – Mar 2016

Technical Skills

  • AI and Machine Learning: Generative AI, LLMs, Deep Learning, PyTorch, TensorFlow, transformers, vLLM
  • High-Performance Computing: Slurm, Jupyter Notebooks, Papermill, distributed computing
  • Programming: Python (advanced), Java, C, NumPy, SciPy, pandas, Matplotlib, Plotly, PyQt
  • Behavioral Experiments and User Studies: oTree Experimental Platform, Django, Prolific for Participant Recruitment
  • Other: Git, Docker, Kubernetes, NLP, HCI, Cybersecurity, Distributed Ledger Technology

Languages

  • German — Native
  • English — Professional working proficiency
  • Latin — Latinum (officially certified)
  • French, Italian, Spanish — Basic

Professional Memberships

  • Association for the Advancement of Artificial Intelligence (AAAI) — International AI research society
  • Gesellschaft für Informatik (GI) — German Informatics Society
  • Bund Deutscher Volks- und Betriebswirte (bdvb) — German Association of Business Economists