AI hallucinations can’t be stopped — but these techniques can limit their damage

When computer scientist Andy Zou researches artificial intelligence (AI), he often asks a chatbot to suggest background reading and references. But this doesn’t always go well. “Most of the time, it gives me different authors than the ones it should, or maybe sometimes the paper doesn’t exist at all,” says Zou, a graduate student at Carnegie Mellon University in Pittsburgh, Pennsylvania.

It’s well known that all kinds of generative AI, including the large language models (LLMs)…