用大语言模型实现理性选择函数并衡量其与用户偏好的一致性
Implementing Rational Choice Functions with LLMs and Measuring their Alignment with User Preferences
AI总结：
本文提出用大语言模型实现理性选择函数的设计原则，并构建工具衡量其与用户偏好（含严格偏好与无差异）的一致性，在汽车领域智能用户界面中验证了方法的有效性。
摘要：
随着大语言模型（LLMs）成为智能用户界面（IUIs）不可或缺的组成部分，其作为决策智能体的角色引发了关于一致性的关键担忧。尽管已有大量研究解决了事实性、偏见和毒性等问题，但相对而言，很少有人关注对偏好一致性的衡量，即不同备选方案的相对可取性，这一概念在决策制定、经济学和社会选择理论中均有使用。然而，一个可靠的决策智能体应做出与用户偏好高度一致的选择。在本文中，我们通过解决与更广泛且更灵活的用户偏好概念（包括严格偏好和备选方案间的无差异）的一致性，推广了现有利用LLMs对备选结果进行排序的方法。为此，我们提出了使用LLMs实现理性选择函数的设计原则，并提供了衡量偏好满足度的必要工具。我们通过在汽车领域实际应用智能用户界面的实证研究，展示了我们方法的适用性。
英文摘要：
As large language models (LLMs) become integral to intelligent user interfaces (IUIs), their role as decision-making agents raises critical concerns about alignment. Although extensive research has addressed issues such as factuality, bias, and toxicity, comparatively little attention has been paid to measuring alignment to preferences, i.e., the relative desirability of different alternatives, a concept used in decision making, economics, and social choice theory. However, a reliable decision-making agent makes choices that align well with user preferences. In this paper, we generalize existing methods that exploit LLMs for ranking alternative outcomes by addressing alignment with the broader and more flexible concept of user preferences, which includes both strict preferences and indifference among alternatives. To this end, we put forward design principles for using LLMs to implement rational choice functions, and provide the necessary tools to measure preference satisfaction. We demonstrate the applicability of our approach through an empirical study in a practical application of an IUI in the automotive domain.
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。
