Symbolic Reasoning about Large Language Models

Guy van den Broeck (UCLA) https://simons.berkeley.edu/talks/guy-van-den-broeck-ucla-2025-04-29 Theoretical Aspects of Trustworthy AI Today, many expect AI to tackle complex problems by performing reasoning—commonly interpreted as large language models generating sequences of tokens that resemble chains of thought. Yet historically, AI reasoning had a very different meaning: executing symbolic algorithms that performed logical or probabilistic deduction to derive definite answers to questions about knowledge. In this talk, I show that such old-fashioned ideas are very relevant to reasoning with large language models today. In particular, I will demonstrate that integrating symbolic reasoning algorithms directly into the architecture of language models enables state-of-the-art capabilities in controllable text generation and alignment.