Saved in:
Bibliographic Details
Main Authors: Lawless, Connor, Schoeffer, Jakob, Le, Lindy, Rowan, Kael, Sen, Shilad, Hill, Cristina St., Suh, Jina, Sarrafzadeh, Bahareh
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.06908
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916419605626880
author Lawless, Connor
Schoeffer, Jakob
Le, Lindy
Rowan, Kael
Sen, Shilad
Hill, Cristina St.
Suh, Jina
Sarrafzadeh, Bahareh
author_facet Lawless, Connor
Schoeffer, Jakob
Le, Lindy
Rowan, Kael
Sen, Shilad
Hill, Cristina St.
Suh, Jina
Sarrafzadeh, Bahareh
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_06908
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle "I Want It That Way": Enabling Interactive Decision Support Using Large Language Models and Constraint Programming
Lawless, Connor
Schoeffer, Jakob
Le, Lindy
Rowan, Kael
Sen, Shilad
Hill, Cristina St.
Suh, Jina
Sarrafzadeh, Bahareh
Human-Computer Interaction
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.
title "I Want It That Way": Enabling Interactive Decision Support Using Large Language Models and Constraint Programming
topic Human-Computer Interaction
url https://arxiv.org/abs/2312.06908