Haolong Hu

Haolong Hu

Auto-generated profile, based on publicly available information

Haolong Hu

The Hong Kong University of Science and Technology (Guangzhou)

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 May 2024
Verified
Conference Paper
Open access
JWJiyao Wang
Jiyao Wang
HHHaolong Hu
Haolong Hu
ZWZuyuan Wang
Zuyuan Wang
SYSong Yan
Song Yan
YSYouyu Sheng
Youyu Sheng
DHDengbo He
Dengbo He
The rapid advancement of large language models (LLMs) such as ChatGPT makes LLM-based academic tools possible. However, little research has empirically evaluated how scholars perform different types of academic tasks with LLMs. Through an empirical study followed by a semi-structured interview, we assessed 48 early-stage scholars’ performance in conducting core academic activities (i.e., paper reading and literature reviews) under different levels of time pressure. Before conducting the tasks, participants received different training programs regarding the limitations and capabilities of the LLMs. After completing the tasks, participants completed an interview. Quantitative data regarding the influence of time pressure, task type, and training program on participants’ performance in academic tasks was analyzed. Semi-structured interviews provided additional information on the influential factors of task performance, participants’ perceptions of LLMs, and concerns about integrating LLMs into academic workflows. The findings can guide more appropriate usage and design of LLM-based tools in assisting academic work.

4 February 2026 in Human Factors: The Journal of the Human Factors and Ergonomics Society
Verified
Journal Article
Closed access
ZWZhenyu Wang
Zhenyu Wang
WXWeiyin Xie
Weiyin Xie
HHHaolong Hu
Haolong Hu
XCXiang Chang
Xiang Chang
MSMeng Sun
Meng Sun
DHDengbo He
Dengbo He
Objective: This study investigates how users’ trust evolves during their first ride in a fully driverless robotaxi and how it can be affected by user characteristics, system design, and traffic scenarios. Background: As driving automation technology matures, driverless robotaxis have become available. Despite its immense economic and social potential, public acceptance can be strongly influenced by user trust. Previous research on trust in autonomous vehicles often relied on surveys, driving simulators, or “Wizard of Oz” methods, potentially introducing biases. Method: An on-road experiment was conducted in commercially operating fully driverless robotaxis on public urban roads. In total, 30 participants with no prior experience riding fully driverless robotaxis were recruited, comprising nondrivers ( n = 10), and drivers with ( n = 10) and without ( n = 10) driving automation experience. Dynamic trust was collected at a 2-min interval during the ride, along with participants’ think-aloud for changes in trust. A cumulative link mixed model was used to assess the impact of past driving experience, demographics, and riding time on trust development. Results: Our findings revealed that dynamic trust increased gradually and stabilized over time, with user heterogeneity playing a moderating role in this process. Further think-aloud data analysis identified key factors in trust formation, including driving style, riding safety and comfort, and user interface design. Conclusion: Trust in driverless robotaxis builds progressively with real-world exposure, shaped by user characteristics, vehicle control, and interface design. Application: Our findings underscore the importance of considering user heterogeneity in fostering trust and acceptance of robotaxis.

22 September 2025
Verified
Conference Paper
Open access
ZWZhenyu Wang
Zhenyu Wang
HHHaolong Hu
Haolong Hu
WXWeiyin Xie
Weiyin Xie
XCXiang Chang
Xiang Chang
PXPeixuan Xiong
Peixuan Xiong
DHDengbo He
Dengbo He