Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools (Paper Explained)

https://www.youtube.com/watch?v=no7EQkOiHQM

«… the thing that people want out of these public research tools I do strongly believe that in the current state applying LLMs like they do is just the fundamentally wrong thing to do. And expecting LLM systems to perform these tasks, these public legal research tasks is just the fundamentally wrong expectation. That’s just not what they are for. And you are trying to apply the things to something that they are not made for. And then you’ll get garbage. …»