THIRDWAVE establishes an international, interdisciplinary network to advance neuro-symbolic foundation models. By integrating Large Language Models (LLMs), Knowledge Graphs (KGs), and symbolic reasoning, THIRDWAVE enables trustworthy, explainable, and domain-specific AI systems. The project addresses challenges in medicine, food systems, geodata, and education through secondments and collaborative research. The four key objectives of this project are:

Understanding LLMs:

Analyzing capabilities and limitations to improve performance, usability, and trustworthiness.

Enhancing LLMs:

Improving fairness, factual accuracy, and robustness through external knowledge sources and human collaboration.

Advancing LLM-driven Neuro-Symbolic AI:

Developing hybrid systems that combine LLMs with symbolic reasoning for structured knowledge representation and better decision support.

Use Cases & Evaluation:

Applying LLM-driven neuro-symbolic AI in healthcare, education, geodata, and food information engineering, validating scalability and societal impact.