《我要的方式》：利用大型语言模型和约束编程实现交互式决策支持

"I Want It That Way": Enabling Interactive Decision Support Using Large Language Models and Constraint Programming

December 12, 2023

作者: Connor Lawless, Jakob Schoeffer, Lindy Le, Kael Rowan, Shilad Sen, Cristina St. Hill, Jina Suh, Bahar Sarrafzadeh

cs.AI

摘要

决策支持系统成功的关键因素之一是准确建模用户偏好。心理学研究表明，用户经常在引导过程中形成自己的偏好，突显了系统与用户互动在开发个性化系统中的关键作用。本文介绍了一种新颖的方法，将大型语言模型（LLMs）与约束编程相结合，以促进交互式决策支持。我们通过会议安排这一日常耗时活动为例，研究了这种混合框架。我们进行了三项研究来评估这一新颖框架，包括一项日记研究（n=64）以描述上下文调度偏好，对系统性能进行定量评估，以及与原型系统进行的用户研究（n=10）。我们的工作突出了混合LLM和优化方法在迭代偏好引导和设计考虑方面的潜力，以构建支持人机协作决策过程的系统。

English

A critical factor in the success of decision support systems is the accurate modeling of user preferences. Psychology research has demonstrated that users often develop their preferences during the elicitation process, highlighting the pivotal role of system-user interaction in developing personalized systems. This paper introduces a novel approach, combining Large Language Models (LLMs) with Constraint Programming to facilitate interactive decision support. We study this hybrid framework through the lens of meeting scheduling, a time-consuming daily activity faced by a multitude of information workers. We conduct three studies to evaluate the novel framework, including a diary study (n=64) to characterize contextual scheduling preferences, a quantitative evaluation of the system's performance, and a user study (n=10) with a prototype system. Our work highlights the potential for a hybrid LLM and optimization approach for iterative preference elicitation and design considerations for building systems that support human-system collaborative decision-making processes.