DeepMind develops SAFE, an AI-based app that can fact-check LLMs

A team of artificial intelligence specialists at Google's DeepMind has developed an AI-based system called SAFE that can be used to fact check the results of LLMs such as ChatGPT. The group has published a paper describing the new AI system and how well it performed on the arXiv preprint server.

ai system app artificial artificial intelligence arxiv chatgpt check computer sciences deepmind google intelligence llms paper results safe team