Comment on How Much Do LLMs Hallucinate in Document Q&A Scenarios? A 172-Billion-Token Study Across Temperatures, Context Lengths, and Hardware Platforms [TLDR: 25%]

RandAlThor@lemmy.ca ⁨11⁩ ⁨hours⁩ ago

This is pretty bonkers. How TF are they fabricating answers???

source
Sort:hotnewtop