LexSumm and LexT5: Benchmarking and Modeling Legal Summarization Tasks in English

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Santosh, T. Y. S. S., Weiss, Cornelius, Grabmair, Matthias
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912070129156096
author Santosh, T. Y. S. S.
Weiss, Cornelius
Grabmair, Matthias
author_facet Santosh, T. Y. S. S.
Weiss, Cornelius
Grabmair, Matthias
contents In the evolving NLP landscape, benchmarks serve as yardsticks for gauging progress. However, existing Legal NLP benchmarks only focus on predictive tasks, overlooking generative tasks. This work curates LexSumm, a benchmark designed for evaluating legal summarization tasks in English. It comprises eight English legal summarization datasets, from diverse jurisdictions, such as the US, UK, EU and India. Additionally, we release LexT5, legal oriented sequence-to-sequence model, addressing the limitation of the existing BERT-style encoder-only models in the legal domain. We assess its capabilities through zero-shot probing on LegalLAMA and fine-tuning on LexSumm. Our analysis reveals abstraction and faithfulness errors even in summaries generated by zero-shot LLMs, indicating opportunities for further improvements. LexSumm benchmark and LexT5 model are available at https://github.com/TUMLegalTech/LexSumm-LexT5.
format Preprint
id arxiv_https___arxiv_org_abs_2410_09527
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LexSumm and LexT5: Benchmarking and Modeling Legal Summarization Tasks in English
Santosh, T. Y. S. S.
Weiss, Cornelius
Grabmair, Matthias
Computation and Language
In the evolving NLP landscape, benchmarks serve as yardsticks for gauging progress. However, existing Legal NLP benchmarks only focus on predictive tasks, overlooking generative tasks. This work curates LexSumm, a benchmark designed for evaluating legal summarization tasks in English. It comprises eight English legal summarization datasets, from diverse jurisdictions, such as the US, UK, EU and India. Additionally, we release LexT5, legal oriented sequence-to-sequence model, addressing the limitation of the existing BERT-style encoder-only models in the legal domain. We assess its capabilities through zero-shot probing on LegalLAMA and fine-tuning on LexSumm. Our analysis reveals abstraction and faithfulness errors even in summaries generated by zero-shot LLMs, indicating opportunities for further improvements. LexSumm benchmark and LexT5 model are available at https://github.com/TUMLegalTech/LexSumm-LexT5.
title LexSumm and LexT5: Benchmarking and Modeling Legal Summarization Tasks in English
topic Computation and Language
url https://arxiv.org/abs/2410.09527