Unlocking Memories with AI: Exploring the Role of AI-Generated Cues in Personal Reminiscing
Jun Li Jeung, Janet Yi-Ching Huang
TL;DR
The paper investigates AI-generated cues to support personal reminiscence anchored to home objects by introducing Treasurefinder, a device that uses an LLM to generate open-ended questions from stories attached to NFC-tagged artifacts. In a qualitative, paired home-study with 12 participants, the authors show that AI-generated prompts can enhance memory recall, elicit new insights about others, and foster reflective discussion, including attention to often-overlooked belongings. The findings demonstrate the feasibility and potential of integrating LLMs into physical reminiscence artifacts to augment memory recollection and social interaction, while highlighting limitations in empathy for sensitive stories and the need for broader, privacy-conscious deployments.
Abstract
While technology-mediated reminiscing has been studied for decades, generating relevant cues to trigger personal reminiscing remains challenging. The potential of AI in generating relevant content across various domains has been recently recognized, yet its use in facilitating reminiscing is still less explored. This work aims to explore the use of AI in supporting the recall of personal memories associated with significant objects at home. We designed Treasurefinder, a device powered by a large language model (LLM) that generates open-ended questions based on stories stored in NFC-tagged physical objects or cards. We conducted an exploratory study with 12 participants, grouped in pairs, to observe reminiscing behaviors when using Treasurefinder. The results showed the AI-generated questions 1) supported individuals to recall the past, 2) provided new insights about the other person, and 3) encouraged reflection. Notably, the device facilitated active memory retrieval related to cherished objects that are often overlooked.