METHODS article
Front. Polit. Sci.
Sec. Politics of Technology
Volume 7 - 2025 | doi: 10.3389/fpos.2025.1601440
This article is part of the Research TopicAI Applications in Administrative Systems and ProcessesView all articles
EVALUATING CHATBOT ARCHITECTURES FOR PUBLIC SERVICE DELIVERY: BALANCING FUNCTIONALITY, SAFETY, ETHICS, AND ADAPTABILITY
Provisionally accepted
- Department of Information and Communication Systems Engineering, School of Sciences, University of the Aegean, Samos, Greece
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
The increasing integration of AI-driven interfaces into public service channels has catalyzed a vibrant discourse on the interplay between technological innovation and the traditional values of public governance. This discussion invites a critical exploration of how emerging chatbot architectures can be aligned with ethical principles and resilient public sector practices. While there is research assessing the potential benefits of integrating chatbots in service delivery, existing evaluation approaches often lack specificity to the unique context of public administration, failing to adequately balance technical performance with crucial ethical considerations, safety requirements, and core public service principles like transparency, fairness, and accountability. This research addresses this critical gap by developing and applying a structured evaluation framework specifically designed for assessing diverse chatbot architectures within the public sector. The methodology offers actionable insights to guide the selection and implementation of chatbot solutions that enhance citizen engagement, streamline government services, and uphold key public service values. A key contribution is the introduction of fifteen pre-assessed evaluation criteria, encompassing areas such as input understanding, error handling, legal compliance, safety, and personalization, which are applied to four distinct chatbot architectures. Our findings indicate that while no single architecture is universally optimal, hybrid retrieval-augmented generation (RAG) systems emerge as the most balanced approach, effectively mitigating the risks of pure generative models while retaining their adaptability. Ultimately, this work provides actionable guidance for policymakers and researchers, supporting informed decisions on the responsible use of chatbots and emphasizing the critical balance between innovation and public trust.
Keywords: politics of technology, Chatbots, Public service delivery, evaluation framework, AI ethics, LLMS
Received: 27 Mar 2025; Accepted: 04 Sep 2025.
Copyright: © 2025 PAPADOPOULOS, Alexopoulos and Charalabidis. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: THEODOROS PAPADOPOULOS, Department of Information and Communication Systems Engineering, School of Sciences, University of the Aegean, Samos, 83200, Greece
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.