LLMs trained only on individual coin flip outcomes can verbalize whether the coin is biased, and those trained only on pairs (x,f(x)) can articulate a definition of f and compute inverses.

We examine how large language models (LLMs) generalize from abstract declarative statements in their training data.

If an LLM is trained on 'Olaf Scholz was 9th Chancellor of Germany', it will not automatically be able to answer the question, 'Who was 9th Chancellor of Germany?'