Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Leveraging Large Language Models for Hybrid Workplace Decision Support

Yujin Kim, Chin-Chia Hsu

TL;DR

This study investigates leveraging large language models (LLMs) to support workspace decisions in desk-sharing hybrid workplaces. It combines a pilot study to identify decision factors, an LLM-driven analysis of workspace suggestions with accompanying explanations, and a user study to assess effectiveness and user perceptions. The results show that LLMs can generate reasonable workspace recommendations and explain their rationale, influencing user choices and increasing perceived convenience, with users valuing explanations for trust and transparency. The work demonstrates the potential of LLM-powered decision support and explainable AI in real-world hybrid work environments, while outlining extensions such as visuals, personalization, and privacy considerations. Overall, the findings suggest LLM-based decision support can reduce search effort and improve workspace satisfaction in hybrid workplaces.

Abstract

Large Language Models (LLMs) hold the potential to perform a variety of text processing tasks and provide textual explanations for proposed actions or decisions. In the era of hybrid work, LLMs can provide intelligent decision support for workers who are designing their hybrid work plans. In particular, they can offer suggestions and explanations to workers balancing numerous decision factors, thereby enhancing their work experience. In this paper, we present a decision support model for workspaces in hybrid work environments, leveraging the reasoning skill of LLMs. We first examine LLM's capability of making suitable workspace suggestions. We find that its reasoning extends beyond the guidelines in the prompt and the LLM can manage the trade-off among the available resources in the workspaces. We conduct an extensive user study to understand workers' decision process for workspace choices and evaluate the effectiveness of the system. We observe that a worker's decision could be influenced by the LLM's suggestions and explanations. The participants in our study find the system to be convenient, regardless of whether reasons are provided or not. Our results show that employees can benefit from the LLM-empowered system for their workspace selection in hybrid workplace.

Leveraging Large Language Models for Hybrid Workplace Decision Support

TL;DR

This study investigates leveraging large language models (LLMs) to support workspace decisions in desk-sharing hybrid workplaces. It combines a pilot study to identify decision factors, an LLM-driven analysis of workspace suggestions with accompanying explanations, and a user study to assess effectiveness and user perceptions. The results show that LLMs can generate reasonable workspace recommendations and explain their rationale, influencing user choices and increasing perceived convenience, with users valuing explanations for trust and transparency. The work demonstrates the potential of LLM-powered decision support and explainable AI in real-world hybrid work environments, while outlining extensions such as visuals, personalization, and privacy considerations. Overall, the findings suggest LLM-based decision support can reduce search effort and improve workspace satisfaction in hybrid workplaces.

Abstract

Large Language Models (LLMs) hold the potential to perform a variety of text processing tasks and provide textual explanations for proposed actions or decisions. In the era of hybrid work, LLMs can provide intelligent decision support for workers who are designing their hybrid work plans. In particular, they can offer suggestions and explanations to workers balancing numerous decision factors, thereby enhancing their work experience. In this paper, we present a decision support model for workspaces in hybrid work environments, leveraging the reasoning skill of LLMs. We first examine LLM's capability of making suitable workspace suggestions. We find that its reasoning extends beyond the guidelines in the prompt and the LLM can manage the trade-off among the available resources in the workspaces. We conduct an extensive user study to understand workers' decision process for workspace choices and evaluate the effectiveness of the system. We observe that a worker's decision could be influenced by the LLM's suggestions and explanations. The participants in our study find the system to be convenient, regardless of whether reasons are provided or not. Our results show that employees can benefit from the LLM-empowered system for their workspace selection in hybrid workplace.
Paper Structure (28 sections, 3 figures, 4 tables)

This paper contains 28 sections, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Physical and Social Factors in Workspace
  4. Large Language Models for Decision Making
  5. Explainable AI and Large Language Models
  6. Pilot Study
  7. Methods
  8. Participants
  9. Pilot Study Results
  10. Workspace Suggestions by LLMs
  11. Prompt and Settings
  12. Workspace Suggestions and Accompanying Reasons Provided by LLMs
  13. User Study
  14. Survey Questionnaire
  15. Participants
  16. ...and 13 more sections

Figures (3)

  • Figure 1: The survey results of the importance of considerations for deciding workspace location. The considerations are displayed from the highest to lowest average by converting responses on a Likert scale into numeric values (1: Not important at all to 5: Extremely important): collaborator location (3.714), amenity (3.619), crowdedness (3.548), regular workspace location (3.500), meeting room location (3.167), and manager's location (2.643).
  • Figure 2: The workplace choices over selection phases. Each level represents decision phase, showing the flows of choices from the first phase to second and third phases.
  • Figure 3: The level of perceived confidence and convenience in decision process. Phase 1; decision by user. Phase 2; workspace suggestion by LLM. Phase 3; workspace suggestion with reasons by LLM.