General
impact 16
Evaluating large language models for accuracy incentivizes hallucinations
Evaluating large language models for accuracy incentivizes hallucinations Nature, Published online: 22 April 2026; doi:10.1038/s41586-026-10549-w Evaluating large language models for accuracy incentivizes hallucinations
Why it matters
The large community will be debating this. Pay attention to how evaluating players respond in the coming weeks.