notesum.ai

Published at October 22

Optimizing LLMs with Direct Preferences: A Data Efficiency Perspective

cs.AI
cs.LG

Released Date: October 22, 2024

Authors: Pietro Bernardelle1, Gianluca Demartini

Aff.: 1The University of Queensland, Brisbane, Australia

Arxiv: https://arxiv.org/abs/2410.16586v1