Using LLMs in sensory service research: initial insights and perspectives

Research output: Journal contributionsJournal articlesResearchpeer-review

Standard

Using LLMs in sensory service research: initial insights and perspectives. / Imschloss, Monika; Sarstedt, Marko; Adler, Susanne J. et al.
In: Service Industries Journal, 2025.

Research output: Journal contributionsJournal articlesResearchpeer-review

Harvard

APA

Vancouver

Imschloss M, Sarstedt M, Adler SJ, Cheah JH. Using LLMs in sensory service research: initial insights and perspectives. Service Industries Journal. 2025. doi: 10.1080/02642069.2025.2479723

Bibtex

@article{8c97bfca53d643f9b24805c75930affd,
title = "Using LLMs in sensory service research: initial insights and perspectives",
abstract = "Researchers have started using large language models (LLMs), such as OpenAI's GPT, to generate synthetic datasets designed to mimic human response behavior. Several studies have systematically compared LLM-generated data with human samples in order to explore LLMs{\textquoteright} ability to mimic consumer decision-making. Extending prior findings, our research sets out to explore how GPT-4o responds to sensory information, and to evaluate its ability to grasp crossmodal correspondences as well as multisensory congruence–as commonly encountered in service settings. Our results indicate that while GPT-4o identifies and describes sensory stimuli accurately, it often fails to replicate the associative meanings and interpretations that humans derive from these stimuli, especially in stand-alone assessments. Our research therefore underscores the need for further exploration of the conditions under which LLMs reliably mirror human responses to sensory stimuli, and the implications of using LLMs in research on sensory-rich service settings.",
keywords = "Generative artificial intelligence, large language models, sensory marketing, service research, servicescape, Management studies",
author = "Monika Imschloss and Marko Sarstedt and Adler, {Susanne J.} and Cheah, {Jun Hwa}",
note = "Publisher Copyright: {\textcopyright} 2025 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.",
year = "2025",
doi = "10.1080/02642069.2025.2479723",
language = "English",
journal = "Service Industries Journal",
issn = "0264-2069",
publisher = "Taylor and Francis Ltd.",

}

RIS

TY - JOUR

T1 - Using LLMs in sensory service research

T2 - initial insights and perspectives

AU - Imschloss, Monika

AU - Sarstedt, Marko

AU - Adler, Susanne J.

AU - Cheah, Jun Hwa

N1 - Publisher Copyright: © 2025 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

PY - 2025

Y1 - 2025

N2 - Researchers have started using large language models (LLMs), such as OpenAI's GPT, to generate synthetic datasets designed to mimic human response behavior. Several studies have systematically compared LLM-generated data with human samples in order to explore LLMs’ ability to mimic consumer decision-making. Extending prior findings, our research sets out to explore how GPT-4o responds to sensory information, and to evaluate its ability to grasp crossmodal correspondences as well as multisensory congruence–as commonly encountered in service settings. Our results indicate that while GPT-4o identifies and describes sensory stimuli accurately, it often fails to replicate the associative meanings and interpretations that humans derive from these stimuli, especially in stand-alone assessments. Our research therefore underscores the need for further exploration of the conditions under which LLMs reliably mirror human responses to sensory stimuli, and the implications of using LLMs in research on sensory-rich service settings.

AB - Researchers have started using large language models (LLMs), such as OpenAI's GPT, to generate synthetic datasets designed to mimic human response behavior. Several studies have systematically compared LLM-generated data with human samples in order to explore LLMs’ ability to mimic consumer decision-making. Extending prior findings, our research sets out to explore how GPT-4o responds to sensory information, and to evaluate its ability to grasp crossmodal correspondences as well as multisensory congruence–as commonly encountered in service settings. Our results indicate that while GPT-4o identifies and describes sensory stimuli accurately, it often fails to replicate the associative meanings and interpretations that humans derive from these stimuli, especially in stand-alone assessments. Our research therefore underscores the need for further exploration of the conditions under which LLMs reliably mirror human responses to sensory stimuli, and the implications of using LLMs in research on sensory-rich service settings.

KW - Generative artificial intelligence

KW - large language models

KW - sensory marketing

KW - service research

KW - servicescape

KW - Management studies

UR - http://www.scopus.com/inward/record.url?scp=105002056612&partnerID=8YFLogxK

U2 - 10.1080/02642069.2025.2479723

DO - 10.1080/02642069.2025.2479723

M3 - Journal articles

AN - SCOPUS:105002056612

JO - Service Industries Journal

JF - Service Industries Journal

SN - 0264-2069

ER -

Recently viewed

Activities

  1. Mobilizing and organizing for transnational solidarity: the case of Exchains
  2. The botherder's lure and the figure of the pirate: trespassing enclosures and tweaking affordances
  3. BMC Medical Informatics and Decision Making (Zeitschrift)
  4. "Value Orientations as Predictors for Sustainable Clothing Consumption"
  5. 7th IFAC Symposium on Robust Control Desing - ROCOND 2012
  6. Charline Monin
  7. Efficiency through Democracy? Concepts and Evidence from Environmental Governance (with O. Fritsch)
  8. Fordham University Press (Verlag)
  9. Unity as Legal Principle of the European Union?
  10. Paulo Freires Vision einer Forschung für Transformation
  11. The Rhetoric of TINA: 'There is no alternative' as an Argument in Politics
  12. Palgrave Macmillan (Verlag)
  13. HyperKult 14
  14. Tagung, Oldenburg
  15. Mitigating Democratic Myopia as a Means to Mitigate Climate Change: On Institutional Innovations, their Impact Potential, and the Challenges of their Institutionalization
  16. 3rd EFACIS Roundtable Discussion - IrEN 2021
  17. Leuphana Universität Lüneburg (Organisation)
  18. Multilingual skills at the transition from school into vocational education and training: Students’ perceptions and experiences
  19. Fakultät Management und Technologie (Organisation)
  20. Computer Assisted Webnography: A new Approach to Online Reputation Management.
  21. „Massive Online Virtual Communities“ 2008
  22. D-Grid All Hands Meeting - 2007
  23. Teaching, assessing and promoting 21st century competencies
  24. Symbolic Environmental Legislation and Societal Self-Deception: The Societal, Technical and Environmental Context
  25. Educating the Educators II
  26. Gamifying Language Learning – Möglichkeiten und Grenzen neuer (digitaler) Zugänge zum Fremdsprachenlernen