There is a 5 month old thread [1] on this, but it might be already outdated.<p>What is the best approach for feeding custom set of documents to LLM and get non-halucinating and decent result in Dec 2023?<p>UPD: The question is generally about how to "teach" LLM answer questions using your set of documents (not necessarily train your own, so approaches like RAG counts)<p>[1] https://news.ycombinator.com/item?id=36832572