4 accepted papers
Mechanistic Interpretability (MI) proposes a path toward fully understanding how neural networks make their predictions. Prior work demonstrates that even when trained to perform simple arithmetic, models can implement a variety of algorithms (sometimes concurrently) depending on initialization and…
Today's best language models still struggle with "hallucinations", factually incorrect generations, which impede their ability to reliably retrieve information seen during training. The *reversal curse*, where models cannot recall information when probed in a different order than was encountered dur…
The monotonic dependence of the outputs of a neural network on some of its inputs is a crucial inductive bias in many scenarios where domain knowledge dictates such behavior. This is especially important for interpretability and fairness considerations. In a broader context, scenarios in which monot…
We aim to understand grokking, a phenomenon where models generalize long after overfitting their training set. We present both a microscopic analysis anchored by an effective theory and a macroscopic analysis of phase diagrams describing learning performance across hyperparameters. We find that gene…