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

Suifang Zhou; Qi Gong; Ximing Shen; Ray LC

doi:10.1145/3772318.3791863

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

Suifang Zhou
, Qi Gong
, Ximing Shen
, Ray LC

School of Creative Media

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

3 Citations (Scopus)

2 Downloads (CityUHK Scholars)

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 default-condition participants who believed they had a clearer understanding of the event were more likely to trust GPT's output, whereas 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 subconsciously affects beliefs and perceptions of remembered events. © 2026 Copyright held by the owner/author(s).

Original language	English
Title of host publication	CHI '26
Subtitle of host publication	Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems
Editors	Nuria Oliver, David A. Shamma, Heloisa Candello, Pablo Cesar, Pedro Lopes, Alessandro Bozzon, Thomas Kosch, Vera Liao, Xiaojuan Ma, Valentino Artizzu, Fiona Draxler, Gustavo López, Anke V. Reinschluessel, Xin Tong, Phoebe O. Toups Dugas
Publisher	Association for Computing Machinery
Number of pages	19
ISBN (Print)	979-8-4007-2278-3
DOIs	https://doi.org/10.1145/3772318.3791863
Publication status	Published - 13 Apr 2026
Event	2026 ACM CHI Conference on Human Factors in Computing Systems (CHI 2026): Creating Tomorrow Together - Centre de Convencions Internacional de Barcelona, Barcelona, Spain Duration: 13 Apr 2026 → 17 Apr 2026 https://chi2026.acm.org/

Publication series

Name	Conference on Human Factors in Computing Systems - Proceedings

Conference

Conference	2026 ACM CHI Conference on Human Factors in Computing Systems (CHI 2026)
Abbreviated title	CHI'26
Place	Spain
City	Barcelona
Period	13/04/26 → 17/04/26
Internet address	https://chi2026.acm.org/

Bibliographical note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Research Keywords

Artificial Intelligence
Large Language Models
memory

Publisher's Copyright Statement

This full text is made available under CC-BY 4.0. https://creativecommons.org/licenses/by/4.0/

Access Output

10.1145/3772318.3791863

491107551.pdfFinal Published version, 4.67 MBLicence: CC BY

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Zhou, S., Gong, Q., Shen, X., & LC, R. (2026). Tell Me What I Missed: Interacting with GPT during Recalling of One-Time Witnessed Events. In N. Oliver, D. A. Shamma, H. Candello, P. Cesar, P. Lopes, A. Bozzon, T. Kosch, V. Liao, X. Ma, V. Artizzu, F. Draxler, G. López, A. V. Reinschluessel, X. Tong, & P. O. T. Dugas (Eds.), CHI '26: Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems Article 803 (Conference on Human Factors in Computing Systems - Proceedings). Association for Computing Machinery. https://doi.org/10.1145/3772318.3791863

Zhou, Suifang ; Gong, Qi ; Shen, Ximing et al. / Tell Me What I Missed : Interacting with GPT during Recalling of One-Time Witnessed Events. CHI '26: Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems. editor / Nuria Oliver ; David A. Shamma ; Heloisa Candello ; Pablo Cesar ; Pedro Lopes ; Alessandro Bozzon ; Thomas Kosch ; Vera Liao ; Xiaojuan Ma ; Valentino Artizzu ; Fiona Draxler ; Gustavo López ; Anke V. Reinschluessel ; Xin Tong ; Phoebe O. Toups Dugas. Association for Computing Machinery, 2026. (Conference on Human Factors in Computing Systems - Proceedings).

@inproceedings{49f44a9b010d48d1bd37dfcd922f5ebc,

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

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 default-condition participants who believed they had a clearer understanding of the event were more likely to trust GPT's output, whereas 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 subconsciously affects beliefs and perceptions of remembered events. {\textcopyright} 2026 Copyright held by the owner/author(s).",

keywords = "Artificial Intelligence, Large Language Models, memory",

author = "Suifang Zhou and Qi Gong and Ximing Shen and Ray LC",

note = "Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).; 2026 ACM CHI Conference on Human Factors in Computing Systems (CHI 2026) : Creating Tomorrow Together, CHI'26 ; Conference date: 13-04-2026 Through 17-04-2026",

year = "2026",

month = apr,

day = "13",

doi = "10.1145/3772318.3791863",

language = "English",

isbn = "979-8-4007-2278-3",

series = "Conference on Human Factors in Computing Systems - Proceedings",

publisher = "Association for Computing Machinery",

editor = "Nuria Oliver and Shamma, \{David A. \} and Heloisa Candello and Pablo Cesar and Pedro Lopes and Bozzon, \{Alessandro \} and Kosch, \{Thomas \} and Vera Liao and Ma, \{Xiaojuan \} and Artizzu, \{Valentino \} and Fiona Draxler and Gustavo L{\'o}pez and Reinschluessel, \{Anke V.\} and Xin Tong and Dugas, \{Phoebe O. Toups\}",

booktitle = "CHI '26",

address = "United States",

url = "https://chi2026.acm.org/",

}

Zhou, S, Gong, Q, Shen, X & LC, R 2026, Tell Me What I Missed: Interacting with GPT during Recalling of One-Time Witnessed Events. in N Oliver, DA Shamma, H Candello, P Cesar, P Lopes, A Bozzon, T Kosch, V Liao, X Ma, V Artizzu, F Draxler, G López, AV Reinschluessel, X Tong & POT Dugas (eds), CHI '26: Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems., 803, Conference on Human Factors in Computing Systems - Proceedings, Association for Computing Machinery, 2026 ACM CHI Conference on Human Factors in Computing Systems (CHI 2026), Barcelona, Spain, 13/04/26. https://doi.org/10.1145/3772318.3791863

Tell Me What I Missed: Interacting with GPT during Recalling of One-Time Witnessed Events. / Zhou, Suifang; Gong, Qi; Shen, Ximing et al.
CHI '26: Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems. ed. / Nuria Oliver; David A. Shamma; Heloisa Candello; Pablo Cesar; Pedro Lopes; Alessandro Bozzon; Thomas Kosch; Vera Liao; Xiaojuan Ma; Valentino Artizzu; Fiona Draxler; Gustavo López; Anke V. Reinschluessel; Xin Tong; Phoebe O. Toups Dugas. Association for Computing Machinery, 2026. 803 (Conference on Human Factors in Computing Systems - Proceedings).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Tell Me What I Missed

T2 - 2026 ACM CHI Conference on Human Factors in Computing Systems (CHI 2026)

AU - Zhou, Suifang

AU - Gong, Qi

AU - Shen, Ximing

AU - LC, Ray

N1 - Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

PY - 2026/4/13

Y1 - 2026/4/13

N2 - 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 default-condition participants who believed they had a clearer understanding of the event were more likely to trust GPT's output, whereas 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 subconsciously affects beliefs and perceptions of remembered events. © 2026 Copyright held by the owner/author(s).

AB - 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 default-condition participants who believed they had a clearer understanding of the event were more likely to trust GPT's output, whereas 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 subconsciously affects beliefs and perceptions of remembered events. © 2026 Copyright held by the owner/author(s).

KW - Artificial Intelligence

KW - Large Language Models

KW - memory

UR - http://www.scopus.com/inward/record.url?scp=105038741840&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105038741840&origin=recordpage

U2 - 10.1145/3772318.3791863

DO - 10.1145/3772318.3791863

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 979-8-4007-2278-3

T3 - Conference on Human Factors in Computing Systems - Proceedings

BT - CHI '26

A2 - Oliver, Nuria

A2 - Shamma, David A.

A2 - Candello, Heloisa

A2 - Cesar, Pablo

A2 - Lopes, Pedro

A2 - Bozzon, Alessandro

A2 - Kosch, Thomas

A2 - Liao, Vera

A2 - Ma, Xiaojuan

A2 - Artizzu, Valentino

A2 - Draxler, Fiona

A2 - López, Gustavo

A2 - Reinschluessel, Anke V.

A2 - Tong, Xin

A2 - Dugas, Phoebe O. Toups

PB - Association for Computing Machinery

Y2 - 13 April 2026 through 17 April 2026

ER -

Zhou S, Gong Q, Shen X, LC R. Tell Me What I Missed: Interacting with GPT during Recalling of One-Time Witnessed Events. In Oliver N, Shamma DA, Candello H, Cesar P, Lopes P, Bozzon A, Kosch T, Liao V, Ma X, Artizzu V, Draxler F, López G, Reinschluessel AV, Tong X, Dugas POT, editors, CHI '26: Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery. 2026. 803. (Conference on Human Factors in Computing Systems - Proceedings). doi: 10.1145/3772318.3791863

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

Abstract

Publication series

Conference

Bibliographical note

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this