Dola Decoding by Contrasting Layers Improves Factuality in Large Language Models

So will LLMs ultimately become realists, or nominalists?

&gt; exploiting the fact that factual knowledge in an LLMs has generally been shown to be localized to particular transformer layers<p>This is surprising

Just call it correctness. Hallucination as an alternative to incorrect is fine for marketing I guess but factuality is especially awkward besides being pretty Orwellian.