4 papers
Bouba Beats Kiki, and Other Regularities in the Subjective Preferences of LLMs
Katy Blumer, Jon Kleinberg, Ravi Kumar +1
Users engage with large language models on tasks that are purely objective ("When was Netflix founded?"), purely subjective ("What should I name my child?") or anywhere in-between.…
Sketching Intersection Profiles: A Simple Proof and Three Applications
Flavio Chierichetti, Mirko Giacchini, Ravi Kumar +3
In this work we settle the complexity of three sketching problems. (i) We show that sketching vertex neighborhood sizes in graphs requires bits, standing in sharp contrast…
Learning Multinomial Logits in time
Flavio Chierichetti, Mirko Giacchini, Ravi Kumar +4
A Multinomial Logit (MNL) model is composed of a finite universe of items , each assigned a positive weight. A query specifies an admissible subset -- called a sl…
Approximating a RUM from Distributions on k-Slates
Flavio Chierichetti, Mirko Giacchini, Ravi Kumar +2
In this work we consider the problem of fitting Random Utility Models (RUMs) to user choices. Given the winner distributions of the subsets of size of a universe, we obtain a p…