Header

UZH-Logo

Maintenance Infos

PROMISE: A Framework for Model-Driven Stateful Prompt Orchestration


Wu, Wenyuan; Heierli, Jasmin; Meisterhans, Max; Moser, Adrian; Färber, Andri; Dolata, Mateusz; Gavagnin, Elena; de Spindler, Alexandre; Schwabe, Gerhard (2024). PROMISE: A Framework for Model-Driven Stateful Prompt Orchestration. In: Islam, Shareeful; Sturm, Arnon. Intelligent Information Systems. Cham: Springer, 157-165.

Abstract

The advent of increasingly powerful language models has raised expectations for conversational interactions. However, controlling these models is a challenge, emphasizing the need to be able to investigate the feasibility and value of their application. We present PROMISE (Available at: https://github.com/zhaw-iwi/promise), a framework that facilitates the development of complex conversational interactions with information systems. Its use of state machine modeling concepts enables model-driven, dynamic prompt orchestration across hierarchically nested states and transitions. This improves the control of language models’ behavior and thus enables their effective and efficient use. We show the applications of PROMISE in health information systems and demonstrate its ability to handle complex interactions.

Abstract

The advent of increasingly powerful language models has raised expectations for conversational interactions. However, controlling these models is a challenge, emphasizing the need to be able to investigate the feasibility and value of their application. We present PROMISE (Available at: https://github.com/zhaw-iwi/promise), a framework that facilitates the development of complex conversational interactions with information systems. Its use of state machine modeling concepts enables model-driven, dynamic prompt orchestration across hierarchically nested states and transitions. This improves the control of language models’ behavior and thus enables their effective and efficient use. We show the applications of PROMISE in health information systems and demonstrate its ability to handle complex interactions.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

1 download since deposited on 24 Jun 2024
1 download since 12 months
Detailed statistics

Additional indexing

Item Type:Book Section, refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Scopus Subject Areas:Social Sciences & Humanities > Management Information Systems
Physical Sciences > Control and Systems Engineering
Social Sciences & Humanities > Business and International Management
Physical Sciences > Information Systems
Physical Sciences > Modeling and Simulation
Social Sciences & Humanities > Information Systems and Management
Scope:Discipline-based scholarship (basic research)
Language:English
Date:29 May 2024
Deposited On:24 Jun 2024 12:21
Last Modified:28 Jun 2024 06:19
Publisher:Springer
Series Name:Lecture Notes in Business Information Processing
Number:520
ISSN:1865-1348
ISBN:9783031609992
OA Status:Closed
Publisher DOI:https://doi.org/10.1007/978-3-031-61000-4_18