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

arXiv: https://arxiv.org/abs/2408.04681 · HTML: https://mlsanity.com/paper/2408.04681/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 37 references that are in the map.
- First posted on arXiv 8 Aug 2024.

## Builds on (most cited first, 7 of 7)

- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Memoro: Using Large Language Models to Realize a Concise Interface for Real-Time Memory Augmentation](https://mlsanity.com/paper/2403.02135/) (2024)
- [Deceptive AI Systems That Give Explanations Are Just as Convincing as Honest AI Systems in Human-Machine Decision Making](https://mlsanity.com/paper/2210.08960/) (2022)

## Built on by (most cited first, 5 of 5)

- [Synthetic Human Memories: AI-Edited Images and Videos Can Implant False Memories and Distort Recollection](https://mlsanity.com/paper/2409.08895/) (2024)
- [SCOPE: Stochastic and Counterbiased Option Placement for Evaluating Large Language Models](https://mlsanity.com/paper/2507.18182/) (2025)
- [If LLMs Have Human-Like Attributes, Then So Does Age of Empires II](https://mlsanity.com/paper/2605.31514/) (2026)
- [If Eleanor Rigby Had Met ChatGPT: A Study on Loneliness in a Post-LLM World](https://mlsanity.com/paper/2412.01617/) (2024)
- [Auditing the Synthetic Memoir: Measuring Scene-Level Confabulation in LLM-Generated Autobiography Against the Documented Record of the Life It Describes](https://mlsanity.com/paper/2608.23640/) (2026)

## Abstract (arXiv)

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.