Language models in question-answering applications may generate hallucinations where they make up information rather than basing answers on source documents.

factualpending

Speaker

Dasha Metropolitansky

Evidence Quote

You want to make sure that the language model is answering those questions based on the source documents, not just making things up.

Source

Claimify: Extracting high-quality claims from language model outputsMicrosoft Research
Created: 8/11/2026, 7:23:06 AM

My Notes

Loading notes...