The research team of the Rényi Institute, Anna Christ Miranda, Adrián Csiszárik, Gergely Becsó, and Dániel Varga, were invited to the Spotlight program at the world's most prestigious artificial intelligence conference, NeurIPS 2025. Their presented article, entitled "The Structure of Relation Decoding Linear Operators in Large Language Models", represents a significant advance in understanding the functioning of large language models.
During their research, they realized that language models do not store isolated facts, but capture the relationships of the world along interconnected conceptual patterns. In other words, the knowledge of the models is not a collection of independent facts, but a system of overlapping relationships organized into common structures. This realization is a step towards a better understanding of how AI works.
The professional jury of the artificial intelligence conference, which looks back on the greatest traditions, divides the incoming studies into four groups. Only a quarter of the studies are accepted, and within that, roughly 10% are divided into two further parts: the Spotlight and Oral categories. The Rényi Institute's artificial intelligence team was thus able to present its research results among the top 3%.
