"I Want It That Way": Enabling Interactive Decision Support Using Large Language Models and Constraint Programming
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _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 |