Google Research· Research

Thinking to recall: How reasoning unlocks parametric knowledge in LLMs

Zorik Gekhman and Jonathan Herzig, Research Scientists, Google Research We study the counterintuitive phenomenon where reasoning helps language models recall simple facts, even when no complex step-by-step solutions are required. We show that this phenomenon is driven by two mechanisms: (1) using generated reasoning tokens to perform latent computation, and (2) generating related facts to prime correct answer recall. Quick links Paper Share Copy link × It is well-established that allowing large language models (LLMs) to generate step-by-step reasoning traces, commonly known as chain-of-thought (CoT), enhances performance on complex tasks. When a model solves difficult math equations, writes software, or answers multi-hop factual questions, breaking the problem down into manageable logical steps is highly effective. However, the utility of this approach remains unclear for simple, single-hop factual questions. For instance, consider a query like: "What year was Mary Engle Pennington inducted into the National Inventors Hall of Fame?" …

Announced

24 Jun 2026 16:51 UTC