Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Unveiling Transformer Perception by Exploring Input Manifolds
Alessandro Benfenati, Alfio Ferrara, Alessio Marta +2
This paper introduces a general method for the exploration of equivalence classes in the input space of Transformer models. The proposed approach is based on sound mathematical the…
cs.LG2025
Modeling Transformers as complex networks to analyze learning dynamics
Elisabetta Rocchetti
The process by which Large Language Models (LLMs) acquire complex capabilities during training remains a key open question in mechanistic interpretability. This project investigate…