FACTS Grounding: A new benchmark for evaluating the factuality of large language models

Google DeepMind ·

Google DeepMind releases FACTS Grounding, a new benchmark with an online leaderboard measuring how accurately LLMs ground responses in provided source material.

Categories: Research

Excerpt

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