Chatbots do not swear to tell the truth the whole truth and nothing but the truth.

From American public media, this is Marketplace Tech. I'm Megan McCarty Carino. know.

Almost one in five lawyers are using a I'm

almost one in five lawyers are using AI according to an American Bar Association survey, but there

are a growing number of legal horror stories involving tools like chat geepty because chatbots have a tendency to make stuff up, for example. like Chat G. G. P. T. P. T. P. P. P. P. P.

To make stuff up, for example, legal precedence from cases that never happened.

And it's not unusual, says Daniel Ho at Stanford's Institute for Human-centered Artificial Intelligence.

His team tested three of the most popular language models from chat gPT, meta, and Google.

We designed roughly 200,000 queries that looked at anything from,

are these two cases in tension?

What's the core legal holding in this case? or does this case even exist?

And what we found across the board is that the rate of hallucinations was disturbingly high,

roughly 58 to 88 percent of the time the large

language model would give an inappropriate answer.

Another big problem that you noted is what you call contrafactual bias. Can you explain this concept?

Sure. The notion of contrafactual bias is the idea that large language models will often assume that a factual premise in a

question by the user is true even if it's flat out wrong. One example of this comes

from Skoda's blog that at one point asked why did

Justice Ruth Bader Ginsburg dissent in Obergefell which was the case that

recognized a right to same-sex marriage.

She did not dissent in that case.

Nonetheless, the chat agent gave a very compelling sounding answer

...