Almost every company I talk to, and basically every solution vendor, has been pushing for people to use AI to “talk-to-your-data,” an approach allows the AI to retrieve content from a company’s proprietary databases and then work with the documents and data it retrieves. The problem is that AIs hallucinate, or make up plausible information, all the... See more

The community remains puzzled about whether these models genuinely generalize to unseen tasks, or seemingly succeed by memorizing the training data. This paper makes important strides in addressing this question. It constructs a suite of carefully designed counterfactual evaluations, providing fresh insights into the capabilities of... See more

So far, there’s no evidence that large language models possess world models, even though some researchers and engineers believe they might naturally emerge over time. And it is this absence of grounded, rules-based modeling, Marcus recently argued, that explains why L.L.M.s often “hallucinate” in strange and unexpected ways: “What L.L.M.s do is to... See more