3 papers
cs.CL2024
PERSONA: A Reproducible Testbed for Pluralistic Alignment
Louis Castricato, Nathan Lile, Rafael Rafailov +2
The rapid advancement of language models (LMs) necessitates robust alignment with diverse user values. However, current preference optimization approaches often fail to capture the…
math.CO2014
An Elementary Proof of the Cayley Formula Using Random Maps
Steven Hao, Andrew He, Ray Li +1
Cayley's formula states that the number of labelled trees on vertices is , and many of the current proofs involve complex structures or rigorous computation. We presen…
math.CO2013
A Simple Proof of the Cayley Formula using Random Graphs
Scott Wu, Ray Li, Andrew He +1
We present a nice result on the probability of a cycle occurring in a randomly generated graph. We then provide some extensions and applications, including the proof of the famous…