3 citations · 3 across the 11 of their papers we have counts for
4 papers · 1 filter
Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks
Tiberiu Musat, Tiago Pimentel, Nicolas Zucchet +1
We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models. While previous works on Transformer learning dynamics h…
Validating Causal Abstraction Metrics on Simulated Complex Systems
Maxime Méloux, Tiago Pimentel, François Portet +1
A central goal of science is to produce valid explanations of complex systems: high-level causal accounts that faithfully reflect the behavior of lower-level mechanisms. Yet no con…
The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?
Denis Sutter, Julian Minder, Thomas Hofmann +1
The concept of causal abstraction got recently popularised to demystify the opaque decision-making processes of machine learning models; in short, a neural network can be abstracte…
Causal Estimation of Memorisation Profiles
Pietro Lesci, Clara Meister, Thomas Hofmann +2
Understanding memorisation in language models has practical and societal implications, e.g., studying models' training dynamics or preventing copyright infringements. Prior work de…