all AI news
Reference-free Monolithic Preference Optimization with Odds Ratio
March 13, 2024, 4:47 a.m. | Jiwoo Hong, Noah Lee, James Thorne
cs.CL updates on arXiv.org arxiv.org
Abstract: While recent preference alignment algorithms for language models have demonstrated promising results, supervised fine-tuning (SFT) remains imperative for achieving successful convergence. In this paper, we study the crucial role of SFT within the context of preference alignment, emphasizing that a minor penalty for the disfavored generation style is sufficient for preference-aligned SFT. Building on this foundation, we introduce a straightforward and innovative reference model-free monolithic odds ratio preference optimization algorithm, ORPO, eliminating the necessity for …
abstract algorithms alignment arxiv context convergence cs.ai cs.cl fine-tuning free language language models optimization paper reference results role sft study style supervised fine-tuning type
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York