Slip Through the Chat: Subtle Injection of False Information in LLM Chatbot Conversation Increases False Memory Formation

AI Ethics, Fairness & AccountabilityMisinformation & Fact-CheckingAI/ML Researchers & EngineersPrivacy Policy Makers

This study examines the potential for malicious generative chatbots to induce false memories by injecting subtle misinformation during user interactions. An experiment involving 180 participants explored five intervention conditions following the presentation of an article: (1) no intervention, (2) reading an honest or (3) misleading article summary, (4) discussing the article with an honest or (5) misleading chatbot. Results revealed that while the misleading summary condition increased false memory occurrence, misleading chatbot interactions led to significantly higher rates of false recollection. These findings highlight the emerging risks associated with conversational AI as it becomes more prevalent. The paper concludes by discussing implications and proposing future research directions to address this concerning phenomenon.

Quick Actions

Share

Share this page

ios_share

https://hci.top/en/papers/iui/195773/2025

AdRecommended

Learn AI Coding at CodeNow

open_in_newOpen DOI Link
DOI: https://doi.org/10.1145/3708359.3712112
At a Glance

Paper Snapshot

fact_check
dataset
Source
IUI
calendar_month
Year
2025
emoji_events
Award
No award tagged
group
Authors
5 authors
sell
Subtopics
AI Ethics, Fairness & Accountability, Misinformation & Fact-Checking
work
Professions
AI/ML Researchers & Engineers, Privacy Policy Makers
article
Content Status
Abstract only
hub
Related Papers
5 related papers