Tell Me What I Missed: Interacting with GPT during Recalling of One-Time Witnessed Events
For researchers and practitioners in human-computer interaction and cognitive science, this work highlights how LLM-assisted recall can subtly influence memory and perception, raising concerns about reliability in eyewitness contexts.
This study investigated how GPT-assisted recall affects memory and perception in a one-time eyewitness scenario. Participants who watched a robbery video and used a default GPT showed a stronger correlation between perceived clarity and trust in GPT output, while those using a guided GPT exhibited better alignment between subjective clarity and actual recall. The work reveals that GPT-user interaction can subconsciously shape beliefs about remembered events.
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.