RELexED: Retrieval-Enhanced Legal Summarization with Exemplar Diversity

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Santosh, T. Y. S. S., Jia, Chen, Goroncy, Patrick, Grabmair, Matthias
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929685438398464
author Santosh, T. Y. S. S.
Jia, Chen
Goroncy, Patrick
Grabmair, Matthias
author_facet Santosh, T. Y. S. S.
Jia, Chen
Goroncy, Patrick
Grabmair, Matthias
contents This paper addresses the task of legal summarization, which involves distilling complex legal documents into concise, coherent summaries. Current approaches often struggle with content theme deviation and inconsistent writing styles due to their reliance solely on source documents. We propose RELexED, a retrieval-augmented framework that utilizes exemplar summaries along with the source document to guide the model. RELexED employs a two-stage exemplar selection strategy, leveraging a determinantal point process to balance the trade-off between similarity of exemplars to the query and diversity among exemplars, with scores computed via influence functions. Experimental results on two legal summarization datasets demonstrate that RELexED significantly outperforms models that do not utilize exemplars and those that rely solely on similarity-based exemplar selection.
format Preprint
id arxiv_https___arxiv_org_abs_2501_14113
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RELexED: Retrieval-Enhanced Legal Summarization with Exemplar Diversity
Santosh, T. Y. S. S.
Jia, Chen
Goroncy, Patrick
Grabmair, Matthias
Computation and Language
This paper addresses the task of legal summarization, which involves distilling complex legal documents into concise, coherent summaries. Current approaches often struggle with content theme deviation and inconsistent writing styles due to their reliance solely on source documents. We propose RELexED, a retrieval-augmented framework that utilizes exemplar summaries along with the source document to guide the model. RELexED employs a two-stage exemplar selection strategy, leveraging a determinantal point process to balance the trade-off between similarity of exemplars to the query and diversity among exemplars, with scores computed via influence functions. Experimental results on two legal summarization datasets demonstrate that RELexED significantly outperforms models that do not utilize exemplars and those that rely solely on similarity-based exemplar selection.
title RELexED: Retrieval-Enhanced Legal Summarization with Exemplar Diversity
topic Computation and Language
url https://arxiv.org/abs/2501.14113