# The Right Model for the Job: An Evaluation of Legal Multi-Label Classification Baselines

arXiv: https://arxiv.org/abs/2401.11852 · HTML: https://mlsanity.com/paper/2401.11852/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 22 Jan 2024.

## Builds on (most cited first, 20 of 20)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [LexGLUE: A Benchmark Dataset for Legal Language Understanding in English](https://mlsanity.com/paper/2110.00976/) (2021)
- [Neural Legal Judgment Prediction in English](https://mlsanity.com/paper/1906.02059/) (2019)
- [ChatGPT: Jack of all trades, master of none](https://mlsanity.com/paper/2302.10724/) (2023)
- [CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction](https://mlsanity.com/paper/1807.02478/) (2018)
- [Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models](https://mlsanity.com/paper/1909.11299/) (2019)
- [Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset](https://mlsanity.com/paper/2207.00220/) (2022)
- [Large-Scale Multi-Label Text Classification on EU Legislation](https://mlsanity.com/paper/1906.02192/) (2019)
- [MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer](https://mlsanity.com/paper/2109.00904/) (2021)
- [CLAUDETTE: an Automated Detector of Potentially Unfair Clauses in Online Terms of Service](https://mlsanity.com/paper/1805.01217/) (2018)
- [Legal Prompt Engineering for Multilingual Legal Judgement Prediction](https://mlsanity.com/paper/2212.02199/) (2022)
- [LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development](https://mlsanity.com/paper/2305.07507/) (2023)
- [Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis](https://mlsanity.com/paper/2010.04543/) (2020)
- [Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domain](https://mlsanity.com/paper/2307.03042/) (2023)
- [Extreme Multi-Label Legal Text Classification: A case study in EU Legislation](https://mlsanity.com/paper/1905.10892/) (2019)
- [Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification](https://mlsanity.com/paper/2007.02439/) (2020)
- [An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text](https://mlsanity.com/paper/2305.05627/) (2023)
- [Processing Long Legal Documents with Pre-trained Transformers: Modding LegalBERT and Longformer](https://mlsanity.com/paper/2211.00974/) (2022)

## Built on by (most cited first, 1 of 1)

- [Taxonomy of Comprehensive Safety for Clinical Agents](https://mlsanity.com/paper/2509.22041/) (2025)

## Abstract (arXiv)

Multi-Label Classification (MLC) is a common task in the legal domain, where more than one label may be assigned to a legal document. A wide range of methods can be applied, ranging from traditional ML approaches to the latest Transformer-based architectures. In this work, we perform an evaluation of different MLC methods using two public legal datasets, POSTURE50K and EURLEX57K. By varying the amount of training data and the number of labels, we explore the comparative advantage offered by different approaches in relation to the dataset properties. Our findings highlight DistilRoBERTa and LegalBERT as performing consistently well in legal MLC with reasonable computational demands. T5 also demonstrates comparable performance while offering advantages as a generative model in the presence of changing label sets. Finally, we show that the CrossEncoder exhibits potential for notable macro-F1 score improvements, albeit with increased computational costs.