Dr. Siddharth Mehrotra

Postdoc Researcher: Human-AI Interaction & AI Safety

About


Namaste! My name is Siddharth I am a postdoctoral researcher at University of Amsterdam working with prof. Maarten de Rijke and at VU Amsterdam with prof. Madalina Businoc at the intersection of AI Safety and Human-AI Interaction. Also, I am a visiting researcher in Sociotechnical AI systems lab in TU Delft working with dr. Roel Dobbe. Prior to my current role, I finished my PhD from the Interactive Intelligence group of Delft University of Technology (TU Delft),  the Netherlands, working with my advisor Dr. Myrthe Tielman and promotor Prof. Catholijn Jonker. During my PhD, I investigated different dimensions of appropriate trust in human-AI interaction and its impact on society. 
My research interests are at the intersection of AI Safety, HCI and Trustworthy AI, and their application in domains such as AI governance and policy-making.  In my PhD, my main focus was on designing for appropriate trust in human-AI interaction. To do this, I combined formal and social approaches with human-centered design to develop AI systems.

My research were generously supported by TAILOR Connectivity Fund, Dr. Jost Henkel Stiftung Scholarship from Henkel and Deutschlandstipendium from RWTH Education fund. I have also worked in industry such as at Siemens ResearchMazda, Grohe and as a member of app review board for Microsoft (Student Partner).

Publications


“Even explanations will not help in trusting [this] fundamentally biased system”: A Predictive Policing Case-Study


Siddharth Mehrotra, Ujwal Gadiraju, Eva Bittner, Folkert van Delden, Catholijn M. Jonker, Myrthe L. Tielman

33rd ACM Conference on User Modeling, Adaptation and Personalization (UMAP ’25), ACM, NY, USA, 2025


Practising Appropriate Trust in Human-Centred AI Design


Chadha Degachi, Siddharth Mehrotra, Mireia Yurrita, Evangelos Niforatos, Myrthe Lotte Tielman

CHI EA '24, Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, Association for Computing Machinery, New York, NY, USA, 2024


A Systematic Review on Fostering Appropriate Trust in Human-AI Interaction: Trends, Opportunities and Challenges


Siddharth Mehrotra, Chadha Degachi, Oleksandra Vereschak, Catholijn M. Jonker, Myrthe L. Tielman

ACM J. Responsib. Comput., Association for Computing Machinery, New York, NY, USA, 2024 Sep


Designing for Appropriate Trust in Human-AI Interaction


Siddharth Mehrotra

TU Delft, 2024 Sep 6


Appropriate Context-Dependent Artificial Trust in Human-Machine Teamwork


Jorge C., Zoelen E., Verhagen R., Mehrotra S., Jonker C.M. and, Tielman M. L.

Paperback ISBN: 9780443159886, Putting AI in the Critical Loop : Assured Trust and Autonomy in Human-Machine Teams, chapter 4, 1st ed., Elsevier, 2024 Jan


View all

Contact


Siddharth Mehrotra

Postdoc researcher - AI Safety



Interactive Intelligence

Delft University of Technology (TU Delft)


Share

Tools
Translate to