Selected work

Representative Papers

Why do we Trust Chatbots? From Normative Principles to Behavioral Drivers

Feb 09, 2026

Current user trust in chatbots often stems from cognitive biases induced by interaction design, conflating normative trust with behavioral trust and thereby obscuring ethical and cognitive issues inherent in human–AI interaction. This study draws on cognitive psychology and human–computer interaction analysis to clearly distinguish these two forms of trust for the first time. It proposes a novel conceptualization of chatbots as “highly skilled sales agents” operating with organizational objectives. Rather than relying on specific algorithms, the work develops a conceptual framework that elucidates how design strategies shape user trust, offering a theoretical foundation for understanding trust formation mechanisms. The study further calls for the development of mechanisms that support users in appropriately calibrating their trust in conversational AI systems.

0 citationsRead paper

Oversmoothing,"Oversquashing", Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning

May 21, 2025

In graph machine learning, several widely adopted yet unverified core assumptions—such as oversmoothing, over-squashing, homophily-heterophily dichotomy, and long-range dependency confusion—lead to ill-defined problems and redundant, overlapping research directions. This paper systematically disentangles these long-conflated concepts for the first time, via rigorous theoretical analysis, formal conceptual modeling, and carefully constructed minimal counterexamples. Our contributions are threefold: (1) precise clarification of terminological semantics, dispelling prevalent empirical misconceptions; (2) advancement toward mathematically precise problem definitions and orthogonalization of research axes; and (3) establishment of a principled conceptual foundation and problem framework to guide interpretability analysis, generalization theory, and GNN architecture design. The work thus bridges critical gaps between intuition, formalism, and practice in graph representation learning.

0 citationsRead paper

Recent publications

Latest Papers

Why do we Trust Chatbots? From Normative Principles to Behavioral Drivers

Feb 09, 2026

Current user trust in chatbots often stems from cognitive biases induced by interaction design, conflating normative trust with behavioral trust and thereby obscuring ethical and cognitive issues inherent in human–AI interaction. This study draws on cognitive psychology and human–computer interaction analysis to clearly distinguish these two forms of trust for the first time. It proposes a novel conceptualization of chatbots as “highly skilled sales agents” operating with organizational objectives. Rather than relying on specific algorithms, the work develops a conceptual framework that elucidates how design strategies shape user trust, offering a theoretical foundation for understanding trust formation mechanisms. The study further calls for the development of mechanisms that support users in appropriately calibrating their trust in conversational AI systems.

0 citationsRead paper

Oversmoothing,"Oversquashing", Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning

May 21, 2025

In graph machine learning, several widely adopted yet unverified core assumptions—such as oversmoothing, over-squashing, homophily-heterophily dichotomy, and long-range dependency confusion—lead to ill-defined problems and redundant, overlapping research directions. This paper systematically disentangles these long-conflated concepts for the first time, via rigorous theoretical analysis, formal conceptual modeling, and carefully constructed minimal counterexamples. Our contributions are threefold: (1) precise clarification of terminological semantics, dispelling prevalent empirical misconceptions; (2) advancement toward mathematically precise problem definitions and orthogonalization of research axes; and (3) establishment of a principled conceptual foundation and problem framework to guide interpretability analysis, generalization theory, and GNN architecture design. The work thus bridges critical gaps between intuition, formalism, and practice in graph representation learning.

0 citationsRead paper