arXiv subjects

Zhengtao Xu

Publications and source records attributed to Zhengtao Xu.

8 recordsLinked to original sources

arXiv2026

Understanding and Supporting Online Discussion with Opinionated Chatbots

Opinionated chatbots are increasingly present on online platforms and have the potential to shape public discourse by influencing individuals' viewpoints before they engage in discussions. Despite their growing presence, the impact of interacting with opinionated chatbots on subsequent online interactions remains largely unexplored. This study investigated how exposure to different types of opinionated chatbots, specifically those expressing opposing, reinforcing, or balanced viewpoints, affected participants' subsequent online discussions. In a controlled experiment with 83 participants, we found that interacting with an opinionated chatbot that consistently opposed participants' arguments led to greater shifts in opinion, indicating enhanced openness to revising one's initial stance. Conversely, participants who interacted with a chatbot that consistently reinforced their views were more likely to adopt more agreeable communication styles in subsequent conversations with others. Furthermore, interactions with different types of opinionated chatbots resulted in varying levels of trust, as well as different perceptions of chatbots and human interlocutors. Our findings indicate that opinionated chatbots can influence both individuals' opinions on social topics and their communication behaviors in online environments. This presents a trade-off for future designers seeking to facilitate cognitive flexibility in changing opinions while maintaining positive user experiences and trust in the chatbots during public discourse. We discuss the implications for designing opinionated chatbots to promote more constructive and less polarized online

cs.HC↗

arXiv2026

Alleviating Linguistic and Interactional Anxiety of Non-Native Speakers in Multilingual Communication

Non-native speakers (NNSs) frequently encounter speaking difficulties in multilingual communication, where existing approaches have shown promise in facilitating NNSs' comprehension and participation in real-time communication. However, they often overlook providing direct speaking support, where anxiety stemming from linguistic inadequacy and uncertain communication dynamics are core issues. To address this, we introduce an AI tool with translation for real-time speaking support. It also builds a channel for mutual understanding with native speakers (NSs) to mitigate interactional anxiety. Through a within-subjects experiment involving 25 NNS-NS pairs (N = 50) on collaborative tasks, our findings suggest that the tool improved NNSs' speaking self-efficacy, reduced their interactional anxiety, and decreased their workload, particularly for NNSs with below-average language proficiency. Furthermore, NNSs reported a significant sense of support from their NS partners via the mutual understanding channel, and NSs also clearly perceived the NNSs' need for assistance and displayed a strong sense of communicative responsibility. This research underscores the potential of AI support in real-time NNS communication and the importance of promoting mutual understanding, culminating in actionable design insights for future work.

cs.HC↗

arXiv2026

InterPilot: Exploring the Design Space of AI-assisted Job Interview Support for HR Professionals

Recruitment interviews are cognitively demanding interactions in which interviewers must simultaneously listen, evaluate candidates, take notes, and formulate follow-up questions. To better understand these challenges, we conducted a formative study with eight HR professionals, from which we derived key design goals for real-time AI support. Guided by these insights, we developed InterPilot, a prototype system that augments interviews through intelligent note-taking and post-interview summary, adaptive question generation, and real-time skill-evidence mapping. We evaluated the system with another seven HR professionals in mock interviews using a within-subjects design. Results show that InterPilot reduced documentation burden without increasing overall workload, but introduced usability trade-offs related to visual attention and interaction complexity. Qualitative findings further reveal tensions around trust and verification when AI suggests highly specific technical questions. We discuss implications for designing future real-time human-AI collaboration in professional settings, highlighting the need to balance assistance granularity, attentional demands, and human agency.

cs.HC↗

arXiv2026

Who You Explain To Matters: Learning by Explaining to Conversational Agents with Different Pedagogical Roles

Conversational agents are increasingly used in education for learning support. An application is "learning by explaining", where learners explain their understanding to an agent. However, existing research focuses on single roles, leaving it unclear how different pedagogical roles influence learners' interaction patterns, learning outcomes and experiences. We conducted a between-subjects study (N=96) comparing agents with three pedagogical roles (Tutee, Peer, Challenger) and a control condition while learning an economics concept. We found that different pedagogical roles shaped learning dynamics, including interaction patterns and experiences. Specifically, the Tutee agent elicited the most cognitive investment but led to high pressure. The Peer agent fostered high absorption and interest through collaborative dialogue. The Challenger agent promoted cognitive and metacognitive acts, enhancing critical thinking with moderate pressure. The findings highlight how agent roles shape different learning dynamics, guiding the design of educational agents tailored to specific pedagogical goals and learning phases.

cs.HC↗

arXiv2025

Understanding the Effects of Miscalibrated AI Confidence on User Trust, Reliance, and Decision Efficacy

Providing well-calibrated AI confidence can help promote users' appropriate trust in and reliance on AI, which are essential for AI-assisted decision-making. However, calibrating AI confidence -- providing confidence score that accurately reflects the true likelihood of AI being correct -- is known to be challenging. To understand the effects of AI confidence miscalibration, we conducted our first experiment. The results indicate that miscalibrated AI confidence impairs users' appropriate reliance and reduces AI-assisted decision-making efficacy, and AI miscalibration is difficult for users to detect. Then, in our second experiment, we examined whether communicating AI confidence calibration levels could mitigate the above issues. We find that it helps users to detect AI miscalibration. Nevertheless, since such communication decreases users' trust in uncalibrated AI, leading to high under-reliance, it does not improve the decision efficacy. We discuss design implications based on these findings and future directions to address risks and ethical concerns associated with AI miscalibration.

cs.AI↗

arXiv2022

Precise electronic structures of amorphous solids: unraveling the color origin and photocatalysis of black titania

Water splitting through efficient catalysts represents an ultimate solution for carbon neutrality within 40 years. To achieve this goal, amorphous photocatalysts are noted for their promising performances. Among them, the best known is black titania (amorphous TiOx, x < 2). However, despite the large number of studies on black titania, its color origin, structure-property relationship, and photocatalytic mechanism remain a topic of hot debate, largely due to the difficulty to calculate its precise electronic structure. Here, using ab initio molecular dynamics simulations, we report the precise electronic structures of black titania and further reveal the generic evolution pattern of the electronic structures of covalent compounds upon amorphization and reduction. Moreover, surface adsorption of the co-catalyst atoms (e.g., Pt) on amorphous substances is simulated for the first time: the disordered surface enables easy accommodation of the co-catalyst atoms, while the extended electronic states facilitate the separation of photo-induced electrons and holes, beneficial for hydrogen evolution. This study elucidates the workings of amorphous catalysts and offers practical guidance for enhancing their performances.

cond-mat.mtrl-sci↗

arXiv2021

Liquefaction-induced Plasticity from Entropy-boosted Amorphous Ceramics

Ceramics are easy to break, and very few generic mechanisms are available for improving their mechanical properties, e.g., the 1975-discovered anti-fracture mechanism is strictly limited to zirconia and hafnia. Here we report a general mechanism for achieving high plasticity through liquefaction of ceramics. We further disclose the general material design strategies to achieve this difficult task through entropy-boosted amorphous ceramics (EBACs), enabling fracture-resistant properties that can withstand severe plastic deformation (e.g., over 95%, deformed to a thickness of a few nanometers) while maintaining high hardness and reduced modulus. The findings reported here open a new route to ductile ceramics and many applications.

cond-mat.mtrl-sci↗

arXiv2013

Low-temperature fabrication of brown TiO2 with enhanced photocatalytic activities under visible light

Titanium dioxide is a photocatalytic substance of great practical importance. However, with its bandgap in the ultraviolet (UV) regime, native forms (undoped) of TiO2 generally exhibits poor photocatalytic activities under visible light. Here we report a facile one-step low-temperature method to treat native TiO2 with NaH in a solution-based protocol. The NaH treatment effectively induces the Ti(III) species and oxygen vacancies into the TiO2 host lattice, and enables the bandgap of TiO2 to be conveniently adjusted from the UV region to the red end of the visible spectrum. The modified TiO2 exhibited significantly enhanced photocatalytic capability under visible light, and lead to faster photo-degradation of organic chemical material. Compared with other ways to reduce the bandgap of TiO2, the approach reported here provides unique advantages for safe, large-scale and economic production of narrow-bandgap TiO2 materials.

physics.chem-ph↗