343 citations · 489 across the 23 of their papers we have counts for
6 papers · 1 filter
Can Interpretation Predict Behavior on Unseen Data?
Victoria R. Li, Jenny Kaufmann, Tian Qin +3
Interpretability research often predicts model responses to targeted mechanistic interventions. But can we predict responses to unseen input data? We propose and demonstrate this a…
Sometimes I am a Tree: Data Drives Unstable Hierarchical Generalization
Tian Qin, Naomi Saphra, David Alvarez-Melis
Early in training, LMs can behave like n-gram models, but eventually they often learn tree-based syntactic rules and generalize hierarchically out of distribution (OOD). We study t…
Attribute Diversity Determines the Systematicity Gap in VQA
Ian Berlot-Attwell, Kumar Krishna Agrawal, A. Michael Carrell +2
Although modern neural networks often generalize to new combinations of familiar concepts, the conditions that enable such compositionality have long been an open question. In this…
TRAM: Bridging Trust Regions and Sharpness Aware Minimization
Tom Sherborne, Naomi Saphra, Pradeep Dasigi +1
Sharpness-aware minimization (SAM) reports improving domain generalization by reducing the loss surface curvature in the parameter space. However, generalization during fine-tuning…
Latent State Models of Training Dynamics
Michael Y. Hu, Angelica Chen, Naomi Saphra +1
The impact of randomness on model training is poorly understood. How do differences in data order and initialization actually manifest in the model, such that some training runs ou…
Linear Connectivity Reveals Generalization Strategies
Jeevesh Juneja, Rachit Bansal, Kyunghyun Cho +2
It is widely accepted in the mode connectivity literature that when two neural networks are trained similarly on the same data, they are connected by a path through parameter space…