How much does background world knowledge affect an LLM's ability to summarize text?

For example, how much does it matter to use a model that implicitly knows an elephant is bigger than a mouse?^[akd]

You can think of summarization as a process to factor out the background knowledge a reasonable listener would take for granted, leaving only the "diff" of interesting meaning.

That implies that the more the LLM understands about the world what a typical human does, the better the summarization will be.

Presumably that ability has a clear logarithmic shape, where more background knowledge gets less and less useful.