2 papers
cs.CL2024
Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models
Emre Onal, Klemens Flöge, Emma Caldwell +2
Fine-tuned Large Language Models (LLMs) often suffer from overconfidence and poor calibration, particularly when fine-tuned on small datasets. To address these challenges, we propo…
cs.LG2023
Neural Collapse in the Intermediate Hidden Layers of Classification Neural Networks
Liam Parker, Emre Onal, Anton Stengel +1
Neural Collapse (NC) gives a precise description of the representations of classes in the final hidden layer of classification neural networks. This description provides insights i…