In this work, we conduct a detailed analysis on the performance of legal-oriented pre-trained language models (PLMs). We examine the interplay between their original objective, acquired knowledge, and legal language understanding capacities which we define as the upstream, probing, and downstream performance, respectively. We consider not only the models’ size but also the pre-training corpora used as important dimensions in our study. To this end, we release a multinational English legal corpus (LeXFiles) and a legal knowledge probing benchmark (LegalLAMA) to facilitate training and detailed analysis of legal-oriented PLMs. We release two new legal PLMs trained on LeXFiles and evaluate them alongside others on LegalLAMA and LexGLUE. We find that probing performance strongly correlates with upstream performance in related legal topics. On the other hand, downstream performance is mainly driven by the model’s size and prior legal knowledge which can be estimated by upstream and probing performance. Based on these findings, we can conclude that both dimensions are important for those seeking the development of domain-specific PLMs.

Cancel Culture as an Internet phenomenon has been previously explored from a social and legal science perspective. This paper demonstrates how Natural Language Processing tasks can be derived from this previous work, underlying techniques on how cancel culture can be measured, identified and evaluated. As part of this paper, we introduce a first cancel culture data set with of over 2.3 million tweets and a framework to enlarge it further. We provide a detailed analysis of this data set and propose a set of features, based on various models including sentiment analysis and emotion detection that can help characterizing cancel culture.