Dr. Tim Schopf

Hi, I’m Tim! 👋

I’m a researcher working at the intersection of natural language processing (NLP) and knowledge engineering, with a focus on making AI systems more reliable, transparent, and useful for science.

Since March 2026, I have been an AI Research Scientist working with Prof. Akiko Aizawa at the National Institute of Informatics (NII). My current work centers on faithful natural language explanations for multimodal claim verification and the development of AI agents for scientific discovery.

Previously, as a postdoctoral researcher at ScaDS.AI, I worked on evidence-based text generation, exploring how LLMs can ground their outputs in traceable evidence. I completed my PhD at the Technical University of Munich, where I investigated NLP and knowledge graph approaches to enhance exploratory searches for scholarly literature.

My current research interests include:

• Understanding, detecting, and mitigating LLM hallucinations (e.g., through faithful explanation generation, automatic claim verification, or grounding outputs in external knowledge)
• Evidence-based text generation (e.g., by attributing, citing, or quoting verifiable sources)
• LLMs for scientific reasoning
• AI agents for scientific discovery

Broadly, I aim to build AI systems that don’t just generate fluent text, but produce reliable, transparent, and scientifically grounded knowledge.