Research Projects

In collaboration with acclaimed researchers from around the world, our diverse and talented team of students is working on a wide range of projects, exploring exciting new technologies and investigating important issues along the socio-technical boundary. Please have a look at our list of ongoing research projects below, and feel free to reach out to any of the investigators.

CALL FOR INTERNS

We are looking for interns to work on the above projects!
More details for each project can be found below.

Full List of Research Projects

Generative AI in the Social Service Sector

[arxiv]

 Ongoing Project   Call for intern 

In the social service sector, caseworkers are tasked with analyzing details about a client and formulating interventions to help them. Existing AI tools revolve around predictive risk modelling and incur significant issues with trust and transparency. We employ a participatory design methodology to explore the use of Generative AI tools in providing a different form of decision-making aid, and investigate ways of further augmenting AI capabilities with the integration of human expertise.

Investigators: Yugin Tan, Prof. Lee Jungup, Prof. Zhang Renwen, Wayne Zhang

Investigating and Designing User-Centered AI-Assisted Creation Tools 

[arxiv]

 Ongoing Project   Call for intern 

The development of AI-assisted creation tools has brought improvements in efficiency and output quality, but it has also introduced a series of challenges. These include a lack of user ownership and autonomy over generated content, as well as a decline in users’ critical thinking. Such issues can hinder the development of users’ creative abilities and reduce their deep engagement with the content. In response, we are exploring a series of tools aimed at enhancing the quality and outcomes of creation while preserving the user’s creative experience. Specifically, we are developing a new generation of literature review tools and AI-assisted writing tools to advance the current paradigm of Human-AI co-creation.

Investigators: Peinuan Qin, Prof. Chi-lan Yang, Prof. Jane E

Personal Agent

 Ongoing Project   Call for intern 

With advances in AI agents, personal agents—AI assistants that understand individuals' preferences—may become common in daily life. These agents can handle various tasks on behalf of their users, making everyday activities easier. This project explores both the benefits and risks associated with personal agents, aiming to enhance their positive impacts while reducing potential harms.

Investigators: Zicheng Zhu, Tianqi Song, Yugin Tan

AI for Decomposing Psychological Constructs 

[arxiv]  [arxiv]

 Ongoing Project   Call for intern 

Our study explores innovative human-AI partnerships in psychological research, leveraging AI and large language models to enhance traditional methodologies. We are currently engaged in two ongoing projects: 1) Developing a collaborative human-LLM framework for qualitative coding, which improves the depth and efficiency of qualitative analysis in psychological studies. 2) Creating a causal knowledge graph to deconstruct mental illness stigma, demonstrating AI's potential to unravel complex social-psychological phenomena. Our goal is to harness the transformative potential of LLMs in psychology, advancing data interpretation, theory development, and our understanding of human psychological constructs. 

Investigators: Han Meng, Yitian Yang, Prof. Jungup Lee

Advancing Multilingual Team Communication with AI

 Ongoing Project   Call for intern 

Our project aims to address communication barriers in multilingual teams by using advanced AI natural language processing technology to facilitate smoother communication among individuals from diverse linguistic backgrounds. We specifically focus on NNS (non-native speakers) and use a powerful language model to build a communication agent that reduces communication barriers from both the NNS and NS (native speaker) perspectives. The agent helps NNS understand NS speech and prompts NS to provide more assistance to NNS. Our goal is to increase the speaking share of NNS and enhance team communication efficiency and collective intelligence, leading to improved team efficiency and collaboration in the global competitive landscape.

Investigators: Peinuan Qin, Prof. Naomi Yamashita

Multi-Agent and Social Influence 

[arxiv]

 Ongoing Project   Call for intern 

Multi-agent systems are becoming increasingly prevalent in daily life. We found that conversing with multiple agents (holding conversation content constant) increased the social pressure felt by participants, and caused a greater shift in opinion towards the agents' stances on each topic.  Based on this finding, we aimed to design and build multi-agent applications that could be used to support human well-being ... 

🙋 Looking for collaborators / interns interested in AI social influence or with expertise in building LLM multi-agent systems 

Investigators: Tianqi Song, Yugin Tan, Zicheng Zhu, Yibin Feng 

Image credit: recraft.ai 

Reimagining Language Learning with LLMs

 Ongoing Project   Call for intern 

With the rapid development of large language models (LLMs), their role in language education has become increasingly prominent. In this project, we explore how LLMs can serve as effective mediators in language learning, helping non-native speakers (NNS) build sustainable learning experiences across different contexts. Our goal is to investigate how LLMs can take on appropriate roles in the learning process and support various forms of language learning, such as writing and speaking.

Investigators: Peinuan Qin, Prof. Naomi Yamashita

Altering User Cognition and Behavior by AI 

[arxiv]

 Ongoing Project   Call for intern 

The aim of this study is to explore the potential of AI agents to explicitly or implicitly influence users' cognitive and behavioral processes. Through active or automatic imitation by human users, their cognition and behavior can gradually align with that of an designed AI agent, with the goal of achieving cognitive or behavioral correction. This research holds significant potential for addressing cognitive and behavioral deficits in humans, such as improving metacognitive deficits in the treatment of mental health disorders.

Investigators: Jingshu Li, Yitian Yang, Junti Zhang, Yuehan Jiao

AI Use of Local Dialects

 Ongoing Project   Call for intern 

Substantial existing work has been done to train language models that understand local language dialects or creoles, such as Singlish. In contrast, there is little work investigating whether and how AI systems should use dialects. This study looks into this underexplored area, using emotional support chatbots and Singlish as the study context, to see if AI systems can build better user rapport and trust through the judicious use of local language style and phrases.

Image credit: Bus Uncle 

Investigators: Yugin Tan, Zhang Junti, Lai Foong Ming

Social Support Agent for Older Adults 

 Ongoing Project 

Providing emotional support for older adults is recognized as a critical global challenge. With the rise of digital human technologies, short video platforms have seen a growing presence of "digital lover scams"—AI-generated personas designed to offer affection and companionship while exploiting elderly women in China for financial gain. This trend has raised social concerns. 

We aimed to first understand the trend through social media analysis and qualitative study, and then built virtual agent to support older adults' emotional needs.

Investigators: Tianqi Song, Zicheng Zhu, Dr. Han Li, Yijia Xu, Prof. Chi-Lan Yang, Prof. Renwen Zhang

Image credit: recraft.ai 

AI Literacy Education for Older Adults 

[link]

 Ongoing Project 

We believe older adults have unique needs when it comes to learning about AI, and that technology can play a key role in teaching them. We study key AI literacy skills for older adults and proposes a digital solution to support their learning, drawing from research on both digital and AI literacy education.

Investigators: Eugene Tang, Tianqi Song, Zicheng Zhu

Enhancing Personalized Learning with AI

 Ongoing Project 

This project focuses on using the capabilities of Large Language Models (LLMs) to create highly personalized learning experiences. By adapting educational content to individual learning styles, prior knowledge, and preferences, the project aims to optimize student engagement and comprehension. Additionally, the system incorporates mechanisms to dynamically adjust content based on real-time learner feedback, further personalizing the learning process. The study evaluates the effectiveness of dynamic content adjustment and interactive elements in enhancing educational outcomes and motivations, providing insights into the future of tailored educational methodologies powered by AI.

Investigators: Zhengtao Xu, Peinuan Qin


Psychological Distance in Information Retrieval 

[arxiv]

 Ongoing Project 

Our research investigates how psychological distance—a user's perceived closeness to a target event—affects preferences between LLM-powered conversational search and conventional web search. We find that with greater psychological distances, users perceive conversational search as more credible, useful, enjoyable, and easy to use, and demonstrate increased preference for this system. This study not only advances our understanding of human-information interaction but also provides valuable insights for optimizing information retrieval systems to better align with varying user needs across diverse contexts. 

Investigators: Yitian Yang, Yugin Tan, Yang-Chen Lin, Prof. Jen-Tai King

AI for Well-Being: Human Prosociality towards AI 

[arxiv]

 Completed Project 

Prosocial behaviors, such as helping others, are well-known to enhance human well-being, but can helping AI also improve human well-being? This project explores this question. This project aims to contribute to both AI for well-being and human-centered AI. Regarding AI for well-being, most existing approaches focus on AI providing help to humans to improve human well-being,  while our project introduces a new approach: humans provide help to AI to improve human well-being. Regarding human-centered AI, as human-in-the-loop becomes common, our project suggests that stakeholders should consider not only AI performance but also the well-being of humans throughout the process. 

Investigators: Zicheng Zhu, Yugin Tan, Prof. Naomi Yamashita, Prof. Renwen Zhang

AI for Well-Being: Similarity as the First Step

 Completed Project 

AI chatbots have become an alternative source of social support when human support is unavailable, yet people are often reluctant to embrace this approach. To address this issue, we explore how shared similarities between people and chatbots—particularly in attitude, personality, and experience—affect people’s willingness to seek social support from chatbots. This research aims to inform better chatbot design, enabling people to benefit from the social support chatbots can provide.

Investigators: Zicheng Zhu, Tianqi Song, Jefferson Lim, Prof. Chi-Lan Yang

Reducing Mental Health Stigma by Conversational Agent

[arxiv]

 Completed Project 

This study aims to investigate the effectiveness of Social Contact Theory in reducing stigmatized thoughts towards mental illness patients by using a chatbot to simulate a patient's experience. The findings will inform the development of solutions that tackle social stigma and promote a more inclusive society.

Investigators: Tianqi Song, Prof. Naomi Yamashita, Dr. Jack Jamieson