Law-Specific Large Language Model Generative AI Interim Report: Lexis+AI Versus GPT-4

As instructed by the good people at Lexis, the writer of the article has been trying to stump LexisAI so that Lexis can use my feedback to improve the product. Hence, this report, which I intended as the sort of constructive criticism I was asked by Lexis to provide.

Lexis is also testing the product at some other law schools and at major law firms but has not released the identities of such firms; I asked the Lexis representative in charge of the Cornell group of testers whether our participation was also supposed to be secret and he said no.

Neither GPT-4 nor Lexis+AI is intended to be used as a substitute for thoughtful research or analysis. As my testing indicates, they should not be used that way, nor even as a uniformly reliable means of accurately identifying and characterizing the law. 

As the bonus round indicates, however, there are already other very productive uses for Lexis+AI, especially with some careful prompt engineering.

Source: Dorf on Law



, ,



Leave a Reply

Your email address will not be published. Required fields are marked *