Ask for sources. Easy.

How do you know anything is correct? LLMs can be wrong, humans can be wrong, you can be wrong. The motto of the royal society, is "Nullius in verba" which is a latin phrase : "take nobody's word for it," that's LITERALLY the motto of the royal society. Its your job as a scientist and critical thinker to test assumptions, oberve reality and use empirical inquiry to seek truth, and in the process, question ALL sources and test all assertions, from multiple angles if required.

amusing that this comment contains a subtle appeal to authority. "take nobody's word for it" -- you can take the Royal Society's word for that

You don't - the way I use LLMs for explanations is that I keep going back and forth between the LLM explanation and Google search /Wikipedia. And of course asking the LLM to cite sources helps.

This might sound cumbersome but without the LLM I wouldn't have (1) known what to search for, in a way (2) that lets me incrementally build a mental model. So it's a net win for me. The only gap I see is coverage/recall: when asked for different techniques to accomplish something, the LLM might miss some techniques - and what is missed depends upon the specific LLM. My solution here is asking multiple LLMs and going back to Google search.

Same way you can tell if the source material is correct. Or indeed, anything you read online. How confident are you in the veracity of any random Wikipedia article or blog?

You use your brain and cross-reference multiple sources.

Even traditional research methods return bogus information. People are just wrong sometimes and you as a researcher have to deal with that.

The way to deal with LLM accuracy is to not trust it blindly. Same as everything. The LLM will try to convince you and itself that it's right even when it isn't. But you can say the same for a shockingly large number of historic works written by explorers and people who had no clue what they were talking about.