16 citations · 31 across the 10 of their papers we have counts for
10 papers
Preference learning made easy: Everything should be understood through win rate
Lily H. Zhang, Rajesh Ranganath
Preference learning, or the task of aligning generative models to preference comparison data, has yet to reach the conceptual maturity of classification, density estimation, etc. T…
Towards Minimal Targeted Updates of Language Models with Targeted Negative Training
Lily H. Zhang, Rajesh Ranganath, Arya Tafvizi
Generative models of language exhibit impressive capabilities but still place non-negligible probability mass over undesirable outputs. In this work, we address the task of updatin…
Preference Learning Algorithms Do Not Learn Preference Rankings
Angelica Chen, Sadhika Malladi, Lily H. Zhang +4
Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner…
Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning
Abhijith Gandrakota, Lily Zhang, Aahlad Puli +4
Anomaly, or out-of-distribution, detection is a promising tool for aiding discoveries of new particles or processes in particle physics. In this work, we identify and address two o…
Don't blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy
Aahlad Puli, Lily Zhang, Yoav Wald +1
Common explanations for shortcut learning assume that the shortcut improves prediction under the training distribution but not in the test distribution. Thus, models trained via th…
When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlations
Rhys Compton, Lily Zhang, Aahlad Puli +1
In machine learning, incorporating more data is often seen as a reliable strategy for improving model performance; this work challenges that notion by demonstrating that the additi…
Robustness to Spurious Correlations Improves Semantic Out-of-Distribution Detection
Lily H. Zhang, Rajesh Ranganath
Methods which utilize the outputs or feature representations of predictive models have emerged as promising approaches for out-of-distribution (OOD) detection of image inputs. Howe…
Set Norm and Equivariant Skip Connections: Putting the Deep in Deep Sets
Lily H. Zhang, Veronica Tozzo, John M. Higgins +1
Permutation invariant neural networks are a promising tool for making predictions from sets. However, we show that existing permutation invariant architectures, Deep Sets and Set T…
Understanding Failures in Out-of-Distribution Detection with Deep Generative Models
Lily H. Zhang, Mark Goldstein, Rajesh Ranganath
Deep generative models (DGMs) seem a natural fit for detecting out-of-distribution (OOD) inputs, but such models have been shown to assign higher probabilities or densities to OOD…
Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations
Aahlad Puli, Lily H. Zhang, Eric K. Oermann +1
In many prediction problems, spurious correlations are induced by a changing relationship between the label and a nuisance variable that is also correlated with the covariates. For…