Integrating Large Language Models and Optimization in Semi- Structured Decision Making: Methodology and a Case Study

Semi-structured decisions, which fall between highly structured and unstructured decision types, rely on human intuition and experience for the final choice, while using data and analytical models to generate tentative solutions. These processes are traditionally iterative and time-consuming, requir...

Full description

Saved in:
Bibliographic Details
Main Authors: Gianpaolo Ghiani, Gianluca Solazzo, Gianluca Elia
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Algorithms
Subjects:
Online Access:https://www.mdpi.com/1999-4893/17/12/582
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850050432484769792
author Gianpaolo Ghiani
Gianluca Solazzo
Gianluca Elia
author_facet Gianpaolo Ghiani
Gianluca Solazzo
Gianluca Elia
author_sort Gianpaolo Ghiani
collection DOAJ
description Semi-structured decisions, which fall between highly structured and unstructured decision types, rely on human intuition and experience for the final choice, while using data and analytical models to generate tentative solutions. These processes are traditionally iterative and time-consuming, requiring cycles of data gathering, analysis, and option evaluation. In this study, we propose a novel framework that integrates Large Language Models (LLMs) with optimization techniques to streamline such decision-making processes. In our approach, LLMs leverage their capabilities in data interpretation, common-sense reasoning, and mathematical modeling to assist decision makers by reducing cognitive load. They achieve this by automating aspects of information processing and option evaluation, while preserving human oversight as a crucial component of the final decision-making process. Another significant strength of our framework lies in its potential to drive the evolution of a new generation of decision support systems (DSSs). Unlike traditional systems that rely on rigid and inflexible interfaces, our approach enables users to express their preferences in a more natural, intuitive, and adaptable manner, substantially enhancing both usability and accessibility. A case study on last-mile delivery system design in a smart city demonstrates the practical application of this framework. The results suggest that our approach has the potential to simplify the decision-making process and improve efficiency by reducing cognitive load, enhancing user experience, and facilitating more intuitive interactions.
format Article
id doaj-art-fa59fa49ab8147f0a216ce9898d05b76
institution DOAJ
issn 1999-4893
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Algorithms
spelling doaj-art-fa59fa49ab8147f0a216ce9898d05b762025-08-20T02:53:27ZengMDPI AGAlgorithms1999-48932024-12-01171258210.3390/a17120582Integrating Large Language Models and Optimization in Semi- Structured Decision Making: Methodology and a Case StudyGianpaolo Ghiani0Gianluca Solazzo1Gianluca Elia2Dipartimento di Ingegneria dell’Innovazione, Università del Salento, Via per Monteroni, 73100 Lecce, ItalyDipartimento di Ingegneria dell’Innovazione, Università del Salento, Via per Monteroni, 73100 Lecce, ItalyDipartimento di Ingegneria dell’Innovazione, Università del Salento, Via per Monteroni, 73100 Lecce, ItalySemi-structured decisions, which fall between highly structured and unstructured decision types, rely on human intuition and experience for the final choice, while using data and analytical models to generate tentative solutions. These processes are traditionally iterative and time-consuming, requiring cycles of data gathering, analysis, and option evaluation. In this study, we propose a novel framework that integrates Large Language Models (LLMs) with optimization techniques to streamline such decision-making processes. In our approach, LLMs leverage their capabilities in data interpretation, common-sense reasoning, and mathematical modeling to assist decision makers by reducing cognitive load. They achieve this by automating aspects of information processing and option evaluation, while preserving human oversight as a crucial component of the final decision-making process. Another significant strength of our framework lies in its potential to drive the evolution of a new generation of decision support systems (DSSs). Unlike traditional systems that rely on rigid and inflexible interfaces, our approach enables users to express their preferences in a more natural, intuitive, and adaptable manner, substantially enhancing both usability and accessibility. A case study on last-mile delivery system design in a smart city demonstrates the practical application of this framework. The results suggest that our approach has the potential to simplify the decision-making process and improve efficiency by reducing cognitive load, enhancing user experience, and facilitating more intuitive interactions.https://www.mdpi.com/1999-4893/17/12/582semi-structured decisionshuman-in-the-loopknowledge discoverylarge language modelslast-mile logistics
spellingShingle Gianpaolo Ghiani
Gianluca Solazzo
Gianluca Elia
Integrating Large Language Models and Optimization in Semi- Structured Decision Making: Methodology and a Case Study
Algorithms
semi-structured decisions
human-in-the-loop
knowledge discovery
large language models
last-mile logistics
title Integrating Large Language Models and Optimization in Semi- Structured Decision Making: Methodology and a Case Study
title_full Integrating Large Language Models and Optimization in Semi- Structured Decision Making: Methodology and a Case Study
title_fullStr Integrating Large Language Models and Optimization in Semi- Structured Decision Making: Methodology and a Case Study
title_full_unstemmed Integrating Large Language Models and Optimization in Semi- Structured Decision Making: Methodology and a Case Study
title_short Integrating Large Language Models and Optimization in Semi- Structured Decision Making: Methodology and a Case Study
title_sort integrating large language models and optimization in semi structured decision making methodology and a case study
topic semi-structured decisions
human-in-the-loop
knowledge discovery
large language models
last-mile logistics
url https://www.mdpi.com/1999-4893/17/12/582
work_keys_str_mv AT gianpaologhiani integratinglargelanguagemodelsandoptimizationinsemistructureddecisionmakingmethodologyandacasestudy
AT gianlucasolazzo integratinglargelanguagemodelsandoptimizationinsemistructureddecisionmakingmethodologyandacasestudy
AT gianlucaelia integratinglargelanguagemodelsandoptimizationinsemistructureddecisionmakingmethodologyandacasestudy