[CuriouslyC]

The TLDR is you can prompt the LLM to take different perspectives than its default, then combine those. If the LLM is estimating a number, the different perspectives give you a distribution over the truth, which shows you the range of biases and the most likely true answer (given wisdom of the crowd). If the LLM is generating non-quantifiable output, you can find the "average" of the answers (using embeddings or other methods) and select that one.

[mistermann]

Ah ok, so both are implemented via a call(s) to the LLM, as opposed to a standard algorithmic approach?

[CuriouslyC]

Once you have bayesian prior distributions (which it makes total sense for llms to estimate) you can do tons of nifty statistical techniques. It's only the bottom layer of the analysis stack that's LLM generated.