Natural Language Processing For Expert Domains (ExpNLP)

At ExpNLP, we work on AI for expert domains. We focus on the real-world impact of AI, asking ourselves “How can AI support experts’ work in complex, high-stakes settings”? This requires us to measure performance, reliability, transparency, and practical value. We highly value qualitative insights, going beyond benchmark scores, and human evaluation.

Our research interests include:

  • Evaluating AI in expert domains: in areas like software engineering, healthcare, and industry, errors are costly and understanding strengths and limitations of AI is critical.
  • Integrating multimodal data in Expert AI: experts deal with many forms of information beyond text, including images, structured data, reports, and other domain-specific signals. Expert AI must effectively combine such data to support real-world expert workflows.
  • Expert–AI interaction and collaboration: we aim to design AI systems that assist rather than replace domain experts, enabling powerful partnerships and better decision-making.
People

PhD Students

Doan

Doan Nam Long Vu

Multimodal AI for mental health

Anna

Anna Mokhova

Expert-AI collaboration in coding

Ruilong

Ruilong Wang

Multimodal RAG systems for automotive applications

Student Theses

We welcome application from B.Sc. and M.Sc. students who want to work on topics relevant to the lab vision. If you are interested, feel free to contact Dr. Simone Balloccu. Include a grades transcript, CV, and initial proposal PDF (or at least a topic proposal).

Concluded

  • Supervised by Dr. Simone Balloccu
    • Enhancing Natural Language Inference in Biomedical Applications Using Large Language Models — Kai Zhao
  • Co-supervised by Ruilong Wang
    • Time-Stamped Graphs for Cross-Year Reasoning in VolksWagen Annual Reports — Karim Abdelrahman
    • Contrast Set Generation for Evaluation QA Models in Annual Report reasoning — Cagin Senemoglu
  • Co-supervised by Doan Nam Long Vu
    • Synthetic Therapist-Client Conversation Generation From Questionnaires — Mohamed Aziz Boudabous
    • Expressive Text-To-Speech Generation and Evaluation for Therapist-Client Dialogues — Marleen Sinsel

Ongoing

  • No ongoing thesis at the moment.

Open positions

  • Postdoctoral Researcher – Expert Judgment in LLMs, with a Focus on Cybersecurity (January – December 2027, apply by 15 November 2026). Read the full announcement.

General info: PhDs, Postdocs, and internships

Outside of currently open positions (if any), applications are considered only from self-funded candidates. Feel free to contact Dr. Simone Balloccu. Provide a CV, degree certification, grades transcript (if applying for PhD), and research statement. We strongly suggest to highlight the overlapping between your proposal and the existing research directions of the ExpNLP.