Yongjie Sun
Biographic Data
| ID | 7357691 |
|---|---|
| NAME | Yongjie Sun |
| GIVEN NAMES | Yongjie |
| FAMILY NAME | Sun |
| SIGNATURE | SUN Y |
| AFFILIATIONS | New York University Shanghai |
| ORCID | 0009-0005-9616-9875 |
| VERIFIED | Yes |
| TOTAL WORKS | 9 |
| TOTAL CITATIONS | 0 |
| AUTHOR COUNT | 9 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2012 |
| LATEST PUBLICATION YEAR | 2026 |
| H-INDEX | 0 |
Appraising the Task
Large Language Model (LLM) and Human Performance in Child Investigative Interviewing Question Formulation Tasks
We compared the performance of large language models (LLMs) and humans with various levels of expertise in child investigative interviewing on tasks related to question formulation. Two tasks were employed: a static Interview Excerpt Task where participants (60 psychologists, 60 naive participants, GPT‐4, and Llama‐2) formulated follow‐up questions to 100 interview excerpts, and a dynamic Avatar Interviewing Task where participants (32 profession…
Retention of Training Effects in Police Officers Following Scalable AI Simulations of Child Sexual Abuse Interviews
Child sexual abuse (CSA) investigations require high‐quality interviews, but maintaining interviewing skills long‐term has been challenging. This study investigated the long‐term effectiveness of avatar‐based interview training for CSA investigations among 478 police officers. Participants were randomly assigned to single booster ( n = 291) or double booster ( n = 187) groups. Following initial training, the single booster group received reinforc…
Using large language model–based artificial intelligence (AI) suspects to train strategic use of evidence
OBJECTIVE: The strategic use of evidence (SUE) is a technique that aims to improve the ability to differentiate between liars and truth-tellers. However, while theoretical training provides guidance on interview techniques, it lacks opportunities for practical application. HYPOTHESES: We created two large language model driven artificial intelligence (AI) suspects with whom participants could simulate interviews and hypothesized that these simula…
Impact of natural and socio-economic factors on varicella incidence in children in Shanghai, 2013-2022
Background: Since varicella is already known to be a globally distributed disease, the focus should be more on its transmissibility or disease burden. The incidence of varicella is affected by natural and socio-economic factors. However, it is unclear how these factors synergetically impact the dynamics of varicella transmission and control. Methods: We conducted a retrospective analysis of varicella cases in children aged 0-17 years from 2013 to…
The cultural flow of monism in dance
This article takes Somatic practice as the starting point to explore the cultural flow and practical application of the concept of ‘mind-body unity’ in both Eastern and Western contexts, focusing on its reception among Chinese dancers. By examining the internationalization of the distinct body philosophies in dance between China and the West, as well as the Eastern body perceptions shaped by Chinese dance education, this study explores how this c…
Large language models (LLMs) as jurors
OBJECTIVE: We explored the potential of large language models (LLMs) in legal decision making by replicating Fraser et al. (2023) mock jury experiment using LLMs (GPT-4o, Claude 3.5 Sonnet, and GPT-o1) as decision makers. We investigated LLMs' reactions to factors that influenced human jurors, including defendant race, social status, number of allegations, and reporting delay in sexual assault cases. HYPOTHESES: We hypothesized that LLMs would sh…
Large language models' knowledge of children's memory and suggestibility
Evaluating Ceop model performance in semi-arid region of China
This study systematically evaluates simulations of near-surface temperature and precipitation using the station observations collected in the semi-arid region of China during the Coordinated Enhanced Observing Period (CEOP) from October 2002 to December 2004 (EOP3 and EOP4). The outputs being evaluated are from eight general circulation models (GCMs) archived by the Coordinated Energy and Water Cycle Observations Project (CEOP), as well as a mult…
No prominent works on this page.
Evaluating Ceop model performance in semi-arid region of China
This study systematically evaluates simulations of near-surface temperature and precipitation using the station observations collected in the semi-arid region of China during the Coordinated Enhanced Observing Period (CEOP) from October 2002 to December 2004 (EOP3 and EOP4). The outputs being evaluated are from eight general circulation models (GCMs) archived by the Coordinated Energy and Water Cycle Observations Project (CEOP), as well as a mult…
Impact of natural and socio-economic factors on varicella incidence in children in Shanghai, 2013-2022
Background: Since varicella is already known to be a globally distributed disease, the focus should be more on its transmissibility or disease burden. The incidence of varicella is affected by natural and socio-economic factors. However, it is unclear how these factors synergetically impact the dynamics of varicella transmission and control. Methods: We conducted a retrospective analysis of varicella cases in children aged 0-17 years from 2013 to…
The cultural flow of monism in dance
This article takes Somatic practice as the starting point to explore the cultural flow and practical application of the concept of ‘mind-body unity’ in both Eastern and Western contexts, focusing on its reception among Chinese dancers. By examining the internationalization of the distinct body philosophies in dance between China and the West, as well as the Eastern body perceptions shaped by Chinese dance education, this study explores how this c…
Large language models (LLMs) as jurors
OBJECTIVE: We explored the potential of large language models (LLMs) in legal decision making by replicating Fraser et al. (2023) mock jury experiment using LLMs (GPT-4o, Claude 3.5 Sonnet, and GPT-o1) as decision makers. We investigated LLMs' reactions to factors that influenced human jurors, including defendant race, social status, number of allegations, and reporting delay in sexual assault cases. HYPOTHESES: We hypothesized that LLMs would sh…
Large language models' knowledge of children's memory and suggestibility
Appraising the Task
Large Language Model (LLM) and Human Performance in Child Investigative Interviewing Question Formulation Tasks
We compared the performance of large language models (LLMs) and humans with various levels of expertise in child investigative interviewing on tasks related to question formulation. Two tasks were employed: a static Interview Excerpt Task where participants (60 psychologists, 60 naive participants, GPT‐4, and Llama‐2) formulated follow‐up questions to 100 interview excerpts, and a dynamic Avatar Interviewing Task where participants (32 profession…
Retention of Training Effects in Police Officers Following Scalable AI Simulations of Child Sexual Abuse Interviews
Child sexual abuse (CSA) investigations require high‐quality interviews, but maintaining interviewing skills long‐term has been challenging. This study investigated the long‐term effectiveness of avatar‐based interview training for CSA investigations among 478 police officers. Participants were randomly assigned to single booster ( n = 291) or double booster ( n = 187) groups. Following initial training, the single booster group received reinforc…
Using large language model–based artificial intelligence (AI) suspects to train strategic use of evidence
OBJECTIVE: The strategic use of evidence (SUE) is a technique that aims to improve the ability to differentiate between liars and truth-tellers. However, while theoretical training provides guidance on interview techniques, it lacks opportunities for practical application. HYPOTHESES: We created two large language model driven artificial intelligence (AI) suspects with whom participants could simulate interviews and hypothesized that these simula…
Deception detection and forensic psychology (4 works) · Human Factors and Ergonomics (4 works) · Memory Processes and Influences (4 works) · Legal psychology (3 works) · Poison control (3 works) · Geography (2 works) · Interview (2 works) · Medicine (2 works) · Adjudication (1 work) · Arid (1 work)