Generate Knowledge with Semantic Graphs and RAG

neuml.hashnode.dev

5 pointsdmezzetti4 comments

Is there different output each time you run this function; does it converge upon true statements predicated by premises?

Is there different output with different system prompts, then?

I haven't noticed that to be the case. Small prompt changes can change the output though as with all LLMs.

What about citations, and indicating provenance of derived knowledge?

"Wikidata, with 12B facts, can ground LLMs to improve their factuality" (2023) https://news.ycombinator.com/context?id=38309408

Good points, as you reference.

I have it on my list to figure out how to cite multiple answer/multiple record citations.