Liben (Ben) Chen
Contact
Education:
-
Ph.D. 2027 (Expected)Information & Decision Sciences, University of Minnesota
-
M.Sc. 2022Data Science, New York University
-
B.B.A. 2020Information Systems, City University of Hong Kong
Expertise:
-
Trustworthy AI
-
Personalization Technology
-
Agent-based Modeling
-
Data-driven Decision Making
Biography
Liben (Ben) Chen is a final-year Ph.D. candidate in Information & Decision Sciences at the Carlson School of Management. His research centers on trustworthy AI, with two complementary focuses: (1) understanding the longitudinal dynamics of the user-system feedback loop under adversarial pressure or regulatory constraints, and (2) designing multi-objective AI systems that jointly optimize predictive performance and trustworthiness properties, such as privacy awareness and adversarial robustness. His research addresses trustworthiness challenges in high-value commercial AI systems, such as recommender systems and LLM-based systems, drawing on a diverse methodological toolkit spanning machine learning, deep learning, agent-based simulation, and analytical modeling.
His dissertation research has been conditionally accepted at Information Systems Research, a leading academic journal in information systems. His other research works are under review or revision at top-tier venues in both information systems and computer science, including INFORMS Journal on Computing and Machine Learning. He has presented his findings at renowned academic conferences in his field, such as CIST, WITS, and SCECR, and has been recognized with honors such as the highly selective Carlson School of Management Dissertation Fellowship. Beyond his research, Liben has been actively involved in the academic community, notably as a reviewer for Management Science and Information Systems Research, and an organizer for the student-organized virtual seminar series ISPOC.
Selected Works & Activities
-
Impact of Data Privacy Regulations on Recommender Systems Performance, Liben Chen, Meizi Zhou, Yicheng Song, and Gediminas Adomavicius, Information Systems Research: Conditional Acceptance
-
Echoes of Manipulation: The Reinforcing Effect of Preference Bias on External Perturbations in Recommender Systems, Liben Chen, Meizi Zhou, Jingjing Zhang, and Gediminas Adomavicius, INFORMS Journal on Computing: Under Major Revision
-
Self-Consistent Machine Learning: An Ensemble Smoothing Approach Based on Prediction Confidence, Liben Chen, Mochen Yang, and Gediminas Adomavicius, Machine Learning: Under Review
-
Are LLM-Based Generative Recommenders Adversarially Robust?, Liben Chen, Xuan Bi, and Gediminas Adomavicius, (2026), INFORMS Summer Workshop on AI for Business (SWAIB)
-
Recommending on a Data Diet: Attribution-Based Data Minimization for Privacy-Aware Recommender Systems, Liben Chen and Gediminas Adomavicius, (2026), Symposium on Statistical Challenges in Electronic Commerce Research (SCECR)