以大型語言模型和限制編程實現互動式決策支援：「我想要這樣」

摘要

決策支援系統成功的關鍵因素之一是準確建模使用者偏好。心理學研究表明，使用者通常在引出過程中形成他們的偏好，突顯系統與使用者互動在發展個性化系統中的關鍵作用。本文介紹了一種新方法，將大型語言模型（LLMs）與約束編程結合，以促進互動式決策支援。我們通過會議安排的角度研究了這種混合框架，這是許多信息工作者每天都要面對的耗時活動。我們進行了三項研究來評估這種新框架，包括一項日誌研究（n=64）來描述情境安排偏好，對系統性能的定量評估，以及一項使用原型系統的使用者研究（n=10）。我們的工作突出了混合LLM和優化方法在迭代偏好引出和設計考慮方面的潛力，以構建支持人機協作決策過程的系統。

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.

以大型語言模型和限制編程實現互動式決策支援：「我想要這樣」

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

摘要

Support