ValueCompass：一个衡量人类与LLM之间上下文价值对齐的框架
ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs
AI总结：
本文提出ValueCompass框架，基于心理学理论和系统性回顾识别并评估人类与AI的价值观对齐，在协作写作、教育、公共部门和医疗保健四个真实场景中揭示了人类与LLMs之间令人担忧的价值观错位，为设计上下文感知的AI对齐策略提供见解。
摘要：
随着AI系统变得越来越先进，确保它们与多样化的个人及社会价值观保持一致变得日益关键。但是，我们如何才能捕捉基本的人类价值观，并评估AI系统在多大程度上与其保持一致呢？我们引入了ValueCompass，这是一个基本价值观框架，基于心理学理论和系统性回顾，用于识别和评估人类与AI的对齐情况。我们应用ValueCompass来衡量人类和大型语言模型（LLMs）在四个真实世界场景中的价值对齐：协作写作、教育、公共部门和医疗保健。我们的发现揭示了人类和LLMs之间令人担忧的错位，例如人类经常支持“国家安全”等价值观，而LLMs在很大程度上拒绝了这些价值观。我们还观察到，价值观在不同场景中存在差异，这突显了对上下文感知的AI对齐策略的需求。我们的工作为设计空间提供了有价值的见解，以实现人类与AI的对齐，为负责任地开发AI系统奠定了基础。
英文摘要：
As AI systems become more advanced, ensuring their alignment with a diverse range of individuals and societal values becomes increasingly critical. But how can we capture fundamental human values and assess the degree to which AI systems align with them? We introduce ValueCompass, a framework of fundamental values, grounded in psychological theory and a systematic review, to identify and evaluate human-AI alignment. We apply ValueCompass to measure the value alignment of humans and large language models (LLMs) across four real-world scenarios: collaborative writing, education, public sectors, and healthcare. Our findings reveal concerning misalignments between humans and LLMs, such as humans frequently endorse values like "National Security" which were largely rejected by LLMs. We also observe that values differ across scenarios, highlighting the need for context-aware AI alignment strategies. This work provides valuable insights into the design space of human-AI alignment, laying the foundations for developing AI systems that responsibly reflect societal values and ethics.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
