用大模型实现符合用户偏好的理性决策，提升智能界面的可信度。
Implementing Rational Choice Functions with LLMs and Measuring their Alignment with User Preferences
- 基于用户偏好设计大模型决策机制，支持严格偏好与无差异选择。
- 提出衡量偏好满足度的工具，在汽车交互场景中验证有效。
- 为大模型在真实应用中做对用户有意义的选择提供方法论。
随着大型语言模型（LLMs）在智能用户界面（IUIs）中的广泛应用，其作为决策代理的角色引发了关于对齐性的关键关注。尽管已有大量研究聚焦于事实性、偏见和毒性等问题，但针对用户偏好对齐——即不同选项相对可取性的测量——的研究仍相对不足。然而，可靠的决策代理应能做出与用户偏好一致的选择。本文通过扩展现有利用大模型排序结果的方法，将对齐性推广至更广泛且灵活的用户偏好概念，涵盖严格偏好与选项间的无差异性。为此，我们提出了使用大模型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。通过在汽车领域一个实际IUI应用中的实证研究，展示了该方法的适用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。