Skip to main content

BRIEF RESEARCH REPORT article

Front. Comput. Sci.
Sec. Human-Media Interaction
Volume 6 - 2024 | doi: 10.3389/fcomp.2024.1456098
This article is part of the Research Topic Hybrid Human Artificial Intelligence: Augmenting Human Intelligence with AI View all articles

Users do not trust recommendations from a large language model more than AI-sourced snippets

Provisionally accepted
Melanie J. McGrath Melanie J. McGrath *Patrick S. Cooper Patrick S. Cooper Andreas Duenser Andreas Duenser
  • Commonwealth Scientific and Industrial Research Organisation (CSIRO), Canberra, Australia

The final, formatted version of the article will be published soon.

    Background: The ability of large language models to generate general purpose natural language represents a significant step forward in creating systems able to augment a range of human endeavors. However, concerns have been raised about the potential for misplaced trust in the potentially hallucinatory outputs of these models.The study reported in this paper is a preliminary exploration of whether trust in the content of output generated by an LLM may be inflated in relation to other forms of ecologically valid, AI-sourced information.Method: Participants were presented with a series of general knowledge questions and a recommended answer from an AI-assistant that had either been generated by an ChatGPT-3 or sourced by Google's AI-powered featured snippets function. We also systematically varied whether the AI-assistant's advice was accurate or inaccurate.Results: Trust and reliance in LLM-generated recommendations were not significantly higher than that of recommendations from a non-LLM source. While accuracy of the recommendations resulted in a significant reduction in trust, this did not differ significantly by AI-application.Using three predefined general knowledge tasks and fixed recommendation sets from the AI-assistant, we did not find evidence that trust in LLM-generated output is artificially inflated, or that people are more likely to miscalibrate their trust in this novel technology than another commonly drawn on form of AI-sourced information.

    Keywords: Trust1, Artificial Intelligence2, large language models3, trust calibration4, HCI5, generative AI6, ChatGPT-37, hallucination8

    Received: 28 Jun 2024; Accepted: 20 Sep 2024.

    Copyright: © 2024 McGrath, Cooper and Duenser. 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: Melanie J. McGrath, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Canberra, Australia

    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.