Thinking to recall: How reasoning unlocks parametric knowledge in LLMs
Google Research
Researchers found that enabling reasoning traces in large language models improves recall of simple factual knowledge stored in model weights, even though no complex reasoning is needed. The study identified two mechanisms: a computational buffer effect where extra tokens provide additional forward passes for refinement, and factual priming where generating related facts acts as a semantic warm-up to retrieve harder-to-access information. Hallucinated intermediate facts significantly reduce final answer accuracy, suggesting that training models to prioritize factually supported reasoning steps could improve reliability.
Why it matters
Generative AI
