90 citations · 125 across the 3 of their papers we have counts for
3 papers
Towards Automated Circuit Discovery for Mechanistic Interpretability
Arthur Conmy, Augustine N. Mavor-Parker, Aengus Lynch +2
Through considerable effort and intuition, several recent works have reverse-engineered nontrivial behaviors of transformer models. This paper systematizes the mechanistic interpre…
Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases
Aengus Lynch, Gbètondji J-S Dovonon, Jean Kaddour +1
The problem of spurious correlations (SCs) arises when a classifier relies on non-predictive features that happen to be correlated with the labels in the training data. For example…
Causal Machine Learning: A Survey and Open Problems
Jean Kaddour, Aengus Lynch, Qi Liu +2
Causal Machine Learning (CausalML) is an umbrella term for machine learning methods that formalize the data-generation process as a structural causal model (SCM). This perspective…