OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

arXiv:2309.11235v2 Announce Type: replace
Abstract: Nowadays, open-source large language models like LLaMA have emerged. Recent developments have incorporated supervised fine-tuning (SFT) and reinforcement learning fine-tuning (RLFT) to align these models with human goals. However, SFT methods treat all training data with mixed quality equally, while RLFT methods require high-quality pairwise or ranking-based preference data. In this study, we present a novel framework, named OpenChat, to advance open-source language models with mixed-quality data. Specifically, we consider the general SFT training data, …

arxiv cs.cl data language language models mixed openchat quality quality data type