4 papers · 1 filter
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…
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…
Stochastic interpolants with data-dependent couplings
Michael S. Albergo, Mark Goldstein, Nicholas M. Boffi +2
Generative models inspired by dynamical transport of measure -- such as flows and diffusions -- construct a continuous-time map between two probability densities. Conventionally, o…
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…