Before being deployed for user-facing applications, developers align Large Language Models (LLMs) to user preferences through a variety of procedures, such as Reinforcement Learning From Human Feedback (RLHF) and Direct Preference Optimization (DPO). Current evaluations of these procedures focus on benchmarks of instruction following, reasoning, and truthfulness. However, human preferences are not universal, and aligning to specific preference sets may have unintended effects. We explore how alignment impacts performance along three axes of global representation: English dialects, multilingualism, and opinions from and about countries worldwide. Our results show that current alignment procedures create disparities between English dialects and global opinions. We find alignment improves capabilities in several languages. We conclude by discussing design decisions that led to these unintended impacts and recommendations for more equitable preference tuning.

翻译：在部署到面向用户的应用程序前，开发者通过多种流程（如基于人类反馈的强化学习（RLHF）和直接偏好优化（DPO））将大型语言模型（LLM）与用户偏好对齐。当前对这些流程的评估侧重于指令遵循、推理和真实性等基准测试。然而，人类偏好并非普适，对齐特定偏好集可能产生意想不到的影响。我们探究对齐如何沿全球代表性的三个维度影响性能：英语方言、多语言能力以及来自世界各国的观点与关于世界的观点。结果表明，当前对齐流程在英语方言与全球观点之间制造了差异。我们发现对齐提升了数种语言的能力。最后，我们讨论了导致这些意外影响的设计决策，并提出了实现更公平偏好调优的建议。