Abstract: Artificial intelligence (AI) systems often fail silently, producing confident but incorrect answers, brittle reasoning or misleading scientific conclusions. This gap motivates a central question: What does it mean for AI to be reliable beyond accuracy? In this talk, we present a unified perspective on reliable AI, grounded in two foundational principles: uncertainty quantification and causal representation learning, and demonstrate how these ideas translate into practical advances in both language learning models (LLMs) and scientific discovery.
We first discuss two uncertainty quantification frameworks for LLMs based on conformal prediction. The first enables uncertainty-aware prediction for application programming interface-only LLMs without logit access, producing compact prediction sets with guaranteed coverage. The second extends conformal factuality to multi-step reasoning, introducing a differentiable formulation that preserves formal guarantees while substantially improving claim retention, addressing hallucinations at scale. We then turn to causal representation learning, arguing that reliability also requires modeling how underlying mechanisms change, not just detecting uncertainty. We present TRACE, a causal framework that captures continuous transitions between mechanisms via identifiable mixtures of atomic causal components, enabling robust generalization to previously unseen regimes.
Finally, we briefly highlight two applications in AI for science. In the first, retrieval-augmented LLMs are used to extract causal biomarker networks for Alzheimer’s disease. In the second, conformal prediction is used to enable reliable atom-level uncertainty estimates in molecular docking and the first rigorous comparison of reliability across docking methods.
Bio: Lu Cheng is an assistant professor in Computer Science at the University of Illinois Chicago. She is the recipient of the National Science Foundation CAREER, Pacific-Asia Conference on Knowledge Discovery and Data Mining Best Paper Award, Google Faculty Research Award, Amazon Research Award, Cisco Research Faculty award, Association for the Advancement of AI New Faculty Highlights, 2022 International Neural Network Society Doctoral Dissertation Award (runner-up) and Arizona State University Engineering Dean’s Dissertation Award, among others. She co-authors two books: Causal Inference and Machine Learning (Chinese) and Socially Responsible AI: Theories and Practices.
Series: See upcoming and previous presentations at CS Seminar Series.