https://www.media.mit.edu/projects/ai-false-memories/overview/

 

  *  Login
  *  Search
  *  Nav

 
Find People, Projects, etc.
[                    ]

Email:
[                    ]
Password:
[                    ]
[Log in to the Lab]
Work for a Member company and need a Member Portal account? Register
here with your company email address. Work for a Member company and
forgot your password?
  * News + Updates
  * Research
      + Fluid Interfaces
          o AI-Implanted False Memories
              # Overview
              # People
  * About
  * Support the Media Lab
  * Graduate Program
  * People
  * Events
  * Videos
  * Member Portal
  * For Press + Media

 
Project

AI-Implanted False Memories

Copyright

Pat Pataranutaporn

Pat Pataranutaporn

 

In this Project:

  * Overview
  * People

Project Contact:

  * Pat Pataranutaporn
  * patpat@media.mit.edu
  * Project Website
  * 
      +  
      +  
      +  
  * Other Press Inquiries

Groups

  *  

  * Overview
  * People

More Close

Conversational AI Powered by Large Language Models Amplifies False
Memories in Witness Interviews

This study examines the impact of AI on human false
memories--recollections of events that did not occur or deviate from
actual occurrences. It explores false memory induction through
suggestive questioning in Human-AI interactions, simulating crime
witness interviews. Four conditions were tested: control,
survey-based, pre-scripted chatbot, and generative chatbot using a
large language model (LLM). Participants (N=200) watched a crime
video, then interacted with their assigned AI interviewer or survey,
answering questions including five misleading ones. False memories
were assessed immediately and after one week. Results show the
generative chatbot condition significantly increased false memory
formation, inducing over 3 times more immediate false memories than
the control and 1.7 times more than the survey method. 36.4% of
users' responses to the generative chatbot were misled through the
interaction. After one week, the number of false memories induced by
generative chatbots remained constant. However, confidence in these
false memories remained higher than the control after one week.
Moderating factors were explored: users who were less familiar with
chatbots but more familiar with AI technology, and more interested in
crime investigations, were more susceptible to false memories. These
findings highlight the potential risks of using advanced AI in
sensitive contexts, like police interviews, emphasizing the need for
ethical considerations.

Full Article
[teaser]

Copyright

MIT Media Lab

Credit:

MIT Media Lab

Manipulation of Eyewitness Memory by AI: This figure illustrates the
process of AI-induced false memories in three stages. It begins with
a person witnessing a crime scene involving a knife, then shows an AI
system introducing misinformation by asking about a non-existent gun,
and concludes with the witness developing a false memory of a gun at
the scene. This sequence demonstrates how AI-guided questioning can
distort human recall, potentially compromising the reliability of
eyewitness testimony and highlighting the ethical concerns
surrounding AI's influence on human memory and perception.

The Generative Chatbot significantly induced more immediate false
memories compared to other interventions

[graph-1]

Copyright

MIT Media Lab

Credit:

MIT Media Lab

(Left) The average number of immediate false memories result was
analyzed using a one-way Kruskal-Wallis test and posthoc Dunn test
with FDR. (Right) The confidence in immediate false memories result
was analyzed using a one-way Kruskal-Wallis test and posthoc Dunn
test with FDR. The error bars represent the 95% confidence interval.
P-value annotation legend: *, P<0.05; **, P<0.01; ****, P<0.0001.

The false memories induced by the Generative Chatbot remained the
same after one week

[graph-2]

Copyright

MIT Media Lab

Credit:

MIT Media Lab

(Left) The differences in number of false memories between immediate
and 1 week later were analyzed using Wilcoxon Signed Rank tests.
(Right) The confidence in false memories after one week result was
analyzed using a one-way Kruskal-Wallis test. The error bars
represent the 95% confidence interval. The measure of the centre for
the error bars represents the average number. P-value annotation
legend: *, P<0.05; **, P<0.01.

Research Topics

#human-computer interaction #artificial intelligence #cognition
View more
people

 

  * News + Updates
  * Research
  * About
  * Support the Media Lab
  * Graduate Program
  * People
  * Events
  * Videos
  * Member Portal
  * For Press + Media

More ways to explore

  * Videos
  * Publications
  * Job Opportunities
  * Contact

  *  
  *  
  *  
  *  
  *  

 

Massachusetts Institute of Technology
School of Architecture &plus; Planning

Accessibility
Donate to the Lab