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.
Due to the occlusion of front vehicles, in most cases, drivers can only be reactive to the lead vehicle directly ahead of it (DLV) in chain braking scenarios. Research on connected vehicles has suggested that the awareness of traffic flow in chain braking scenarios can improve traffic safety. Thus, in a video simulation experiment, we explored the safety benefits and users’ acceptance of two windshield-displayed V2V-communication-based HMIs that inform the chain braking events, one with streaming video from the camera in front of the DLV (vHMI) and the other with warning sign informing chain braking events (sHMI). We found that both HMIs improved drivers' understanding of the situation and reduced reaction time and braking response time (BRT) compared to that of the baseline condition (without HMIs). Further, users reported higher usability and satisfaction with sHMI. This research highlights the benefits of providing front-traffic information to drivers in chain braking scenarios.
Silent automation failures, where a system fails to detect a hazard without warning, pose a critical safety challenge for partially automated vehicles. While research has mostly focused on takeover requests, how to support a driver in silent failure remains underexplored. We conducted a multi-modal driving simulator study with 48 participants to investigate how different Prospective Situation Awareness Enhancement (PSAE) interfaces, delivered via augmented reality head-up display, affect takeover performance. By integrating behavioral, subjective psychological, and physiological data, our analysis suggests that situational awareness (SA) serves as an important moderating factor through which PSAE interfaces improve takeover performance. Further, we found that providing perceptual cues was most effective in enhancing SA, while communicating system intent was superior for building trust. Finally, we identified a potential correlate of SA in the neuroactivity. Overall, this paper contributes to understanding how transparency-oriented interfaces may support drivers and provides design insights into HMI design for silent failures.
15 August 2026 in International Journal of Human-Computer Studies
1. With the advent and growing adoption of driving automation technologies, the automotive industry is undergoing a transformative shift expected to benefit the traffic system, including reduced dr...
With the prevalence of smart cockpits, passengers spend increasingly more time engaging with non-driving related tasks (NDRTs, e.g., in-vehicle entertainment and meetings) in vehicles. However, prolonged NDRT engagement can cause sensory conflict and result in motion sickness. Previous research found that motion sickness is highly associated with head motion, which can further be influenced by the positions of the NDRT displays. To guide the design of the smart cockpit, this paper examines the impact of four common NDRT display locations on passengers’ motion sickness. A motion transfer function was utilized to translate a real-world vehicle trajectory into head motion when passengers looked at displays at different locations. Then, a 6 Degree-of-Freedom subjective vertical conflict model was adopted to evaluate the motion sickness caused by head motion. The results of this study can inform the design of in-vehicle displays and improve passenger comfort.