FACTS Grounding: A new benchmark for evaluating the factuality of large language models
deepmind.google
Our comprehensive benchmark and online leaderboard offer a much-needed measure of how accurately LLMs ground their responses in provided source material and avoid hallucinations
  • A_A@lemmy.worldEnglish
    1·
    4 months ago

    On average we humans are getting more stupid, while AI systems are becoming better … even though they are not smart yet.