LexGLUE: A Benchmark Dataset for Legal Language Understanding in English
Ilias Chalkidis, Abhik Jana, Dirk Hartung, Michael Bommarito, Ion Androutsopoulos, Daniel Martin Katz, Nikolaos Aletras
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/coastalcph/lex-glueOfficialIn paperpytorch★ 244
Abstract
Laws and their interpretations, legal arguments and agreements\ are typically expressed in writing, leading to the production of vast corpora of legal text. Their analysis, which is at the center of legal practice, becomes increasingly elaborate as these collections grow in size. Natural language understanding (NLU) technologies can be a valuable tool to support legal practitioners in these endeavors. Their usefulness, however, largely depends on whether current state-of-the-art models can generalize across various tasks in the legal domain. To answer this currently open question, we introduce the Legal General Language Understanding Evaluation (LexGLUE) benchmark, a collection of datasets for evaluating model performance across a diverse set of legal NLU tasks in a standardized way. We also provide an evaluation and analysis of several generic and legal-oriented models demonstrating that the latter consistently offer performance improvements across multiple tasks.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| LexGLUE | BERT | CaseHOLD | 70.7 | — | Unverified |
| LexGLUE | Legal-BERT | CaseHOLD | 75.1 | — | Unverified |
| LexGLUE | CaseLaw-BERT | CaseHOLD | 75.6 | — | Unverified |
| LexGLUE | BigBird | CaseHOLD | 70.4 | — | Unverified |
| LexGLUE | Longformer | CaseHOLD | 72 | — | Unverified |
| LexGLUE | RoBERTa | CaseHOLD | 71.7 | — | Unverified |
| LexGLUE | DeBERTa | CaseHOLD | 72.1 | — | Unverified |