Saved in:
Bibliographic Details
Main Authors: Zhu, Xuyang, Chang, Sejoon, Kuik, Andrew
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.16883
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908334599176192
author Zhu, Xuyang
Chang, Sejoon
Kuik, Andrew
author_facet Zhu, Xuyang
Chang, Sejoon
Kuik, Andrew
contents Retrieval-Augmented Generation (RAG) systems offer a powerful approach to enhancing large language model (LLM) outputs by incorporating fact-checked, contextually relevant information. However, fairness and reliability concerns persist, as hallucinations can emerge at both the retrieval and generation stages, affecting users' reasoning and decision-making. Our research explores how tailored warning messages -- whose content depends on the specific context of hallucination -- shape user reasoning and actions in an educational quiz setting. Preliminary findings suggest that while warnings improve accuracy and awareness of high-level hallucinations, they may also introduce cognitive friction, leading to confusion and diminished trust in the system. By examining these interactions, this work contributes to the broader goal of AI-augmented reasoning: developing systems that actively support human reflection, critical thinking, and informed decision-making rather than passive information consumption.
format Preprint
id arxiv_https___arxiv_org_abs_2504_16883
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Critical Thinking with AI: A Tailored Warning System for RAG Models
Zhu, Xuyang
Chang, Sejoon
Kuik, Andrew
Human-Computer Interaction
Retrieval-Augmented Generation (RAG) systems offer a powerful approach to enhancing large language model (LLM) outputs by incorporating fact-checked, contextually relevant information. However, fairness and reliability concerns persist, as hallucinations can emerge at both the retrieval and generation stages, affecting users' reasoning and decision-making. Our research explores how tailored warning messages -- whose content depends on the specific context of hallucination -- shape user reasoning and actions in an educational quiz setting. Preliminary findings suggest that while warnings improve accuracy and awareness of high-level hallucinations, they may also introduce cognitive friction, leading to confusion and diminished trust in the system. By examining these interactions, this work contributes to the broader goal of AI-augmented reasoning: developing systems that actively support human reflection, critical thinking, and informed decision-making rather than passive information consumption.
title Enhancing Critical Thinking with AI: A Tailored Warning System for RAG Models
topic Human-Computer Interaction
url https://arxiv.org/abs/2504.16883