Gagandeep Singh

University of Illinois Urbana-Champaign

Gagandeep Singh is an Assistant Professor in the Siebel School of Computing and Data Science at the University of Illinois Urbana-Champaign (UIUC). He co-leads the Science and Technology working group at the Institute of Government and Public Affairs, University of Illinois. His research combines ideas from formal methods, machine learning, and systems research to develop systematic and theoretically principled approaches for constructing intelligent computing systems with formal guarantees about their behavior and safety. His group at UIUC has received several awards and fellowships, including the NSF Career, Google Research Scholar, multiple Amazon Research Awards, Qualcomm Innovation Fellowship, and Bloomberg Infrastructure & Security Research Ph.D. Fellowship.

Talk

Title: Formal Methods for the Era of LLMs

Abstract: Formal methods are often dismissed as too rigid, complex, or unscalable for frontier models. In this talk, I will challenge this assumption with both theoretical insights and empirical evidence across various domains, including chatbots, mathematical reasoning, code generation, and agentic AI. I will present a new range of efficient formal frameworks for LLMs that:

Specify and statistically certify safety properties (e.g., fairness, catastrophic risk), yielding stronger generalization guarantees than standard evaluation methods such as benchmarks or red teaming.

Guide generation with semantic guardrails, ensuring outputs respect formal constraints, substantially improving both reasoning performance and safety.

Discover interpretable logical rules that are predictive of and causally relevant to LLM behavior.

Train models that are more performant and safer.

Together, these advances demonstrate that formal methods provide a principled foundation for improving the utility, safety, and efficiency of frontier LLMs.