G. Cattan

IBM Automation and AI, Krakow, Poland

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Interpretability & Mechanistic Interp (1)Natural Language Processing (1)

Frequent co-authors

S. Konior (1)Alexandre Quemy (1)Przemyslaw Klocek (1)B. Sobieski (1)

Papers (1)

Jul 8, 2026

5d ago·also Hother, Warsaw

Riemannian Geometry for Pre-trained Language Model Embeddings

Riemannian Mean Pooling reveals that leveraging geometric properties of embeddings can significantly enhance classification performance while avoiding pitfalls of annotation-driven biases.

S. Konior, Alexandre Quemy, Przemyslaw Klocek +2

Interpretability & Mechanistic Interp Natural Language Processing

Search

G. Cattan

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)