Generative foundation models are susceptible to implicit biases that can arise from extensive unsupervised training data. Such biases can produce suboptimal samples, skewed outcomes, and unfairness, with potentially serious consequences. Consequently, aligning these models with human ethics and preferences is an essential step toward ensuring their responsible and effective deployment in real-world applications. Prior research has primarily employed Reinforcement Learning from Human Feedback (RLHF) to address this problem, where generative models are fine-tuned with RL algorithms guided by a human-feedback-informed reward model. However, the inefficiencies and instabilities associated with RL algorithms frequently present substantial obstacles to the successful alignment, necessitating the development of a more robust and streamlined approach. To this end, we introduce a new framework, Reward rAnked FineTuning (RAFT), designed to align generative models effectively. Utilizing a reward model and a sufficient number of samples, our approach selects the high-quality samples, discarding those that exhibit undesired behavior, and subsequently enhancing the model by fine-tuning on these filtered samples. Our studies show that RAFT can effectively improve the model performance in both reward learning and other automated metrics in both large language models and diffusion models.

翻译：生成式基础模型容易受到无监督训练数据中隐含偏见的干扰，这些偏见可能导致次优样本、偏斜结果及不公平性，甚至引发严重后果。因此，将这些模型与人类伦理和偏好对齐，是确保其在现实应用中负责任且有效部署的关键步骤。现有研究主要采用基于人类反馈的强化学习（RLHF）方法解决该问题，即通过人类反馈训练的奖励模型引导强化学习算法微调生成模型。然而，强化学习算法固有的低效性和不稳定性常常为成功对齐带来重大障碍，亟需开发更稳健高效的方案。为此，我们提出新框架——奖励排序微调（RAFT），旨在有效对齐生成模型。该方法通过奖励模型和充足样本，筛选高质量样本并剔除不符合期望行为的样本，随后基于这些过滤后的样本微调模型以提升性能。研究表明，RAFT在大型语言模型和扩散模型中均能有效提升奖励学习指标及其他自动化评估指标的性能。