In this paper, we develop FinBERT, a state-of-the-art large language model that adapts to the finance domain. Using a sample of researcher-labeled sentences from analyst reports, we document that FinBERT significantly outperforms the Loughran and McDonald dictionary and other machine learning...

Using 321 circuit court rulings, we construct a measure that captures the within-country variation in courts’ attitudes toward securities law violations. Case-level analyses confirm that district courts heed home-circuit precedents and are more likely to dismiss pending cases when their home...