In legal due diligence, lawyers identify a variety of topic instances in a company’s contracts that may pose risk during a transaction. In this paper, we present a study of 9 lawyers conducting a simulated review of 50 contracts for five topics. We find that lawyers agree on the general location of relevant material at a higher rate than in other assessor agreement studies, but they do not entirely agree on the extent of the relevant material. Additionally, we do not find strong differences between lawyers who have differing levels of due diligence expertise.
If we train machine learning models to identify these topics based on each user’s judgments, the resulting models exhibit similar levels of agreement between each other as to the lawyers that trained them. This indicates that these models are learning the types of behaviour exhibited by their trainers, even if they are doing so imperfectly. Accordingly, we argue that additional work is necessary to improve the assessment process to ensure that all parties agree on identified material.