most citedBED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design

1 citations · 1 across the 1 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2025

Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs

Batu El, Deepro Choudhury, Pietro Liò +1

We introduce Attention Graphs, a new tool for mechanistic interpretability of Graph Neural Networks (GNNs) and Graph Transformers based on the mathematical equivalence between mess…