Fathoming the Unfathomable Foundation Models: From Algorithmic Understanding to Scientific Discovery

ABSTRACT

As foundation models become central to information systems, cybersecurity, and scientific decision-making, their opacity raises critical challenges for trust, accountability, and governance. While much prior work has focused on post-hoc explainability, my research shows that such approaches are intrinsically limited and can even obscure model failures. In this talk, I present a shift from explaining opaque systems to designing trustworthy and interpretable AI by construction. I will introduce diagnostic frameworks that reveal failures in explanation faithfulness and security, such as explanatory inversion and vulnerability to retrieval and communication attacks. I will then demonstrate how concept-based, human-centered model architectures enable glass-box reasoning, actionable interventions, and self-reflection for large language models (LLMs). I will conclude by illustrating how these ideas translate into real-world impact across AI-driven cybersecurity, conversational agents, agricultural robotics, and neuroscience, and by outlining a vision for information-centric AI systems that are transparent, reliable, and aligned with human values.

BIOGRAPHY

Zhen Tan is a final-year Ph.D. candidate in Computer Science at Arizona State University, advised by Prof. Huan Liu. His research focuses on trustworthy and explainable artificial intelligence, with an emphasis on understanding and controlling the behavior of large language models and multi-agent systems, and their application in interdisciplinary domains. His work has been published in leading venues, including ICLR, NeurIPS, ICML, KDD, AAAI, ACL, and EMNLP, and has received multiple recognitions, including the CPAL Rising Star Award 2026 and the Best Paper Award at PAKDD 2024.