Responsible Multimodal Information Delivery in Human-AI Interactions.
Are you ready to push the frontiers of meaningful AI and human interaction? Do you thrive on transforming innovative ideas into breakthroughs that redefine how we access, use, and trust information? Join a vibrant, interdisciplinary team at TU Delft to explore the dynamics of intelligent interactive systems in a world where digital interactions shape our decisions-and our future.
Artificial Intelligence (AI)-empowered interactive systems are transforming how people access, process, and apply information. Take the pervasive use of LLMs, for instance, in ChatGPT as an example. These systems empower users to complete tasks more efficiently, from asking simple queries to navigating complex safety-critical scenarios, such as health advice or disaster response. They can organize, summarize, and prioritize information, making them valuable for users seeking quick and actionable insights and recommendations. However, these capabilities also raise critical questions about how intelligent interactive systems deliver information and how these interactions ultimately influence user trust and decision-making.
Key challenges emerge when users face information overload (too much information, leading to confusion or missed priorities), information underload (insufficient details, resulting in a lack of confidence in the advice), or over-reliance (uncritical acceptance of system outputs, even when they may be incorrect or lack context). These interactions depend on system design factors, such as what information is selected, how much information is presented and prioritized, how recommendations are explained, the confidence expressed in the responses, and the presence or absence of warnings. These interactions also depend on users as they differ in their transient and fixed psychological states as well as experience, knowledge, goals, cognitive capacities, attention levels, and decision-making. The way interactive intelligent systems select and deliver information to a user can determine whether they interpret the outputs effectively, trust the system appropriately, and make informed decisions. It also can determine whether the result of user-system interaction is safe and reliable outcomes.
In this PhD project, you will investigate these phenomena to design and evaluate responsible methods in human-AI interaction when interacting with generative information and receiving recommendations. By studying user behavior, preferences, and decision-making in diverse contexts (e.g., safety-critical, non-safety-related), you will aim to develop adaptive and responsible intelligent interactive systems that enhance trust in a safe manner, without encouraging over-reliance or skepticism. Your findings will contribute to the creation of AI tools that are reliable, explainable, context-aware, and aligned with the diverse needs of users and their contexts.
Your Key Responsibilities
- Conducting a systematic review of the literature to identify how information delivery influences the outcomes of the interaction.
- Designing and conducting mixed-methods research by combining qualitative (e.g., user interviews) and quantitative (e.g., surveys, experiments) studies to capture real-world experiences and expectations with intelligent interactive systems.
- Developing a prototype intelligent interactive system capable of manipulating variables, such as explanation, the amount of detail, prioritization of recommendations, and confidence indicators, for experimental testing.
- Conducting experiments using the prototype in simulated scenarios to evaluate how information delivery affects trust, decision accuracy, and user engagement.
- Delivering actionable guidelines and recommendations for designing intelligent interactive systems that provide recommendations, information delivery, and explanations responsibly, ensuring appropriate trust and effective decision-making across diverse contexts.
Department Multi-Actor Systems
You'll be part of the Department Multi-Actor Systems (MAS) within TU Delft's Faculty of Technology, Policy and Management. Our diverse team brings together expertise from both social and engineering sciences. This interdisciplinary approach is essential as we tackle complex sociotechnical challenges such as climate change, cybersecurity, and the energy transition.
- A master's degree (or equivalent) in Human-Computer Interaction, Computer Science, Artificial Intelligence, Data Science, Applied Psychology, Human Factors, or a related discipline.
- You have a multidisciplinary background that covers user aspects/psychology, research methods, and engineering skills in the field of AI.
- Experience with research methodologies, including qualitative (e.g., user studies) and quantitative (e.g., statistical analysis, experimental design) approaches.
- Proficiency in programming languages such as Python or similar, with experience in developing prototypes or intelligent interactive systems.
- Strong academic writing skills, with a strong interest in publishing in peer-reviewed journals.
- .
TU Delft
Delft University of Technology is built on strong foundations. As creators of the world-famous Dutch waterworks and pioneers in biotech, TU Delft is a top international university combining science, engineering and design. It delivers world class results in education, research and innovation to address challenges in the areas of energy, climate, mobility, health and digital society. For generations, our engineers have proven to be entrepreneurial problem-solvers, both in business and in a social context.
At TU Delft we embrace diversity as one of our core values and we actively engage to be a university where you feel at home and can flourish. We value different perspectives and qualities. We believe this makes our work more innovative, the TU Delft community more vibrant and the world more just. Together, we imagine, invent and create solutions using technology to have a positive impact on a global scale. That is why we invite you to apply. Your application will receive fair consideration.
Challenge. Change. Impact!
Faculty Technology, Policy and Management
The Faculty of TPM provides an important contribution to solving complex technical-social issues, such as energy transition, mobility, digitalisation, water management and (cyber) security. TPM does this with its excellent education and research at the intersection of technology, society and policy. We combine insights from both engineering and social sciences as well as the humanities. TPM develops robust models and designs, is internationally oriented and has an extensive network of knowledge institutions, companies, social organisations and governments.
to go to the website of the Faculty of Technology, Policy and Management.
Conditions of employment
Doctoral candidates will be offered a 4-year period of employment in principle, but in the form of 2 employment contracts. An initial 1,5 year contract with an official go/no go progress assessment within 1