March 13, 2024, 4:42 a.m. | Pulkit Pattnaik, Rishabh Maheshwary, Kelechi Ogueji, Vikas Yadav, Sathwik Tejaswi Madhusudhan

cs.LG updates on arXiv.org arxiv.org

arXiv:2403.07230v1 Announce Type: cross
Abstract: Direct Preference Optimization (DPO) is an effective technique that leverages pairwise preference data (usually one chosen and rejected response pair per user prompt) to align LLMs to human preferences. In practice, multiple responses can exist for a given prompt with varying quality relative to each other. With availability of such quality ratings for multiple responses, we propose utilizing these responses to create multiple preference pairs for a given prompt. Our work focuses on systematically using …

abstract alignment arxiv cs.ai cs.cl cs.lg curriculum curriculum learning data direct preference optimization human llms multiple optimization per practice prompt quality responses type

Senior Data Engineer

@ Displate | Warsaw

Decision Scientist

@ Tesco Bengaluru | Bengaluru, India

Senior Technical Marketing Engineer (AI/ML-powered Cloud Security)

@ Palo Alto Networks | Santa Clara, CA, United States

Associate Director, Technology & Data Lead - Remote

@ Novartis | East Hanover

Product Manager, Generative AI

@ Adobe | San Jose

Associate Director – Data Architect Corporate Functions

@ Novartis | Prague