Tell Me What I Missed: Tell Me What I Missed: Interacting with GPT during Recalling of One-Time Witnessed Events

2026-01-29

AI Summary

This study investigates the role of large language models (LLMs) in supporting episodic memory recall following a one-time witnessed event and examines how user–LLM interaction modalities influence both memory accuracy and subjective metacognitive judgments. Participants viewed a simulated robbery video and subsequently recalled details using either a default GPT interface or a guided GPT interface designed according to standard eyewitness protocols. Integrating behavioral experiments with interaction log analysis, the findings reveal that guided prompting significantly enhances recall accuracy and alignment between subjective confidence and objective performance, while also shaping participants’ assessments of the legal culpability of individuals in the event. In contrast, the default GPT interface encouraged users to spontaneously adopt diverse retrieval strategies. The results demonstrate that LLM interactions can subtly reshape users’ memory beliefs, offering a novel pathway toward trustworthy human–AI collaborative memory systems.

Technology Category

Machine Learning: Large Multimodal Models (LMMs)Cognitive Modeling & Cognitive Systems: Social Cognition And InteractionHumans and AI: Interaction Techniques and Devices

Application Category

User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendationSemantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsSearch and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

LLM-assisted technologies are increasingly used to support cognitive processing and information interpretation, yet their role in aiding memory recall, and how people choose to engage with them, remains underexplored. We studied participants who watched a short robbery video (approximating a one-time eyewitness scenario) and composed recall statements using either a default GPT or a guided GPT prompted with a standardized eyewitness protocol. Results show that, in the default condition, participants who believed they had a clearer understanding of the event were more likely to trust GPT's output, whereas in the guided condition, participants showed stronger alignment between subjective clarity and actual recall. Additionally, participants evaluated the legitimacy of the individuals in the incident differently across conditions. Interaction analysis further revealed that default-GPT users spontaneously developed diverse strategies, including building on existing recollections, requesting potentially missing details, and treating GPT as a recall coach. This work shows how GPT-user interplay can subconsciously shape beliefs and perceptions of remembered events.

Problem

• memory recall
• eyewitness testimony
• human-AI interaction
• large language models
• cognitive assistance

Innovation

• LLM-assisted memory recall
• eyewitness testimony
• human-AI interaction
• GPT prompting strategies
• cognitive offloading