IDEAS home Printed from https://ideas.repec.org/a/gam/jsoctx/v15y2025i5p127-d1649695.html

AI Response Quality in Public Services: Temperature Settings and Contextual Factors

Author

Listed:
  • Domenico Trezza

    (Department of Social Sciences, University of Naples Federico II, 80138 Napoli, NA, Italy)

  • Giuseppe Luca De Luca Picione

    (Department of Economics, Management and Institutions, University of Naples Federico II, 80138 Napoli, NA, Italy)

  • Carmine Sergianni

    (Department of Economics, Management and Institutions, University of Naples Federico II, 80138 Napoli, NA, Italy)

Abstract

This study investigated how generative Artificial Intelligence (AI) systems—now increasingly integrated into public services—respond to different technical configurations, and how these configurations affect the perceived quality of the outputs. Drawing on an experimental evaluation of Govern-AI , a chatbot designed for professionals in the social, educational, and labor sectors, we analyzed the impact of the temperature parameter—which controls the degree of creativity and variability in the responses—on two key dimensions: accuracy and comprehensibility . This analysis was based on 8880 individual evaluations collected from five professional profiles. The findings revealed the following: (1) the high-temperature responses were generally more comprehensible and appreciated, yet less accurate in strategically sensitive contexts; (2) professional groups differed significantly in their assessments, where trade union representatives and regional policy staff expressed more critical views than the others; (3) the type of question —whether operational or informational—significantly influenced the perceived output quality. This study demonstrated that the AI performance was far from neutral: it depended on technical settings, usage contexts, and the profiles of the end users. Investigating these “behind-the-scenes” dynamics is essential for fostering the informed governance of AI in public services, and for avoiding the risk of technology functioning as an opaque black box within decision-making processes.

Suggested Citation

  • Domenico Trezza & Giuseppe Luca De Luca Picione & Carmine Sergianni, 2025. "AI Response Quality in Public Services: Temperature Settings and Contextual Factors," Societies, MDPI, vol. 15(5), pages 1-17, May.
    • Handle: RePEc:gam:jsoctx:v:15:y:2025:i:5:p:127-:d:1649695
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2075-4698/15/5/127/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2075-4698/15/5/127/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Anca Florentina Vatamanu & Mihaela Tofan, 2025. "Integrating Artificial Intelligence into Public Administration: Challenges and Vulnerabilities," Administrative Sciences, MDPI, vol. 15(4), pages 1-23, April.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Li, Xin & Zou, Kaicheng & Liao, Tianhu, 2026. "Fiscal transparency, public service provision, and criminal offense rates," International Review of Financial Analysis, Elsevier, vol. 109(C).
    2. Issara Sereewatthanawut & Patipan Sriphon & Pattrawut Khunwipusit & Babatunde Oluwaseun Ajayi & Ademola Enitan Ilesanmi & Jutarat Suwaree & Wonlop Writthym Buachoom, 2026. "Efficient AI-driven allegation screening: A case study of Thailand’s National Anti-Corruption Commission," PLOS ONE, Public Library of Science, vol. 21(1), pages 1-20, January.
    3. Ð . Ð . Nosikov, 2025. "AI-Driven Public Services: A Taxonomy of Accountability and Sovereign Artificial Intelligence (AI)," Administrative Consulting, Russian Presidential Academy of National Economy and Public Administration. North-West Institute of Management., issue 5.
    4. Wiston Mbhazima Baloyi, 2025. "A Systematic Analysis of Ethical and Governance Concerns Relating to Artificial Intelligence Adoption in the South African Public Sector," International Journal of Research and Innovation in Social Science, International Journal of Research and Innovation in Social Science (IJRISS), vol. 9(9), pages 3177-3190, September.
    5. Saša Zdravković & Filip Dobrić & Zoran Injac & Violeta Lukić-Vujadinović & Milinko Veličković & Branka Bursać Vranješ & Srđan Marinković, 2025. "AI-Driven Safety Evaluation in Public Transport: A Case Study from Belgrade’s Closed Transit Systems," Sustainability, MDPI, vol. 17(18), pages 1-36, September.
    6. Sebastian Avacaritei, Ana-Maria Bercu, 2026. "Administrative Resilience In The Era Of Artificial Intelligence: From Digitalization To Algorithmic Governance," European Journal of Public Administration Research, Alexandru Ioan Cuza University, Faculty of Economics and Business Administration, vol. 0, pages 19-40, April.
    7. Loredana Maria Clim (Moga) & Mariana Man & Ionica Oncioiu, 2025. "Mapping Territorial Disparities in Artificial Intelligence Adoption Across Local Public Administrations: Multilevel Evidence from Germany," Administrative Sciences, MDPI, vol. 15(7), pages 1-21, July.

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jsoctx:v:15:y:2025:i:5:p:127-:d:1649695. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager The email address of this maintainer does not seem to be valid anymore. Please ask MDPI Indexing Manager to update the entry or send us the correct address (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.