@inproceedings{bendahman-etal-2025-hallucinations,
title = "Not all Hallucinations are Good to Throw Away When it Comes to Legal Abstractive Summarization",
author = "Bendahman, Nihed and
Pinel-Sauvagnat, Karen and
Hubert, Gilles and
Billami, Mokhtar Boumedyen",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.275/",
pages = "5331--5344",
ISBN = "979-8-89176-189-6",
abstract = "Automatic summarization of legal documents requires a thorough understanding of their specificities, mainly with respect to the vocabulary used by legal experts. Indeed, the latter rely heavily on their external knowledge when writing summaries, in order to contextualize the main entities of the source document. This leads to reference summaries containing many abstractions, that sota models struggle to generate. In this paper, we propose an entity-driven approach aiming at learning the model to generate factual hallucinations, as close as possible to the abstractions of the reference summaries. We evaluated our approach on two different datasets, with legal documents in English and French. Results show that our approach allows to reduce non-factual hallucinations and maximize both summary coverage and factual hallucinations at entity-level. Moreover, the overall quality of summaries is also improved, showing that guiding summarization with entities is a valuable solution for legal documents summarization."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bendahman-etal-2025-hallucinations">
<titleInfo>
<title>Not all Hallucinations are Good to Throw Away When it Comes to Legal Abstractive Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nihed</namePart>
<namePart type="family">Bendahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Pinel-Sauvagnat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gilles</namePart>
<namePart type="family">Hubert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mokhtar</namePart>
<namePart type="given">Boumedyen</namePart>
<namePart type="family">Billami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Automatic summarization of legal documents requires a thorough understanding of their specificities, mainly with respect to the vocabulary used by legal experts. Indeed, the latter rely heavily on their external knowledge when writing summaries, in order to contextualize the main entities of the source document. This leads to reference summaries containing many abstractions, that sota models struggle to generate. In this paper, we propose an entity-driven approach aiming at learning the model to generate factual hallucinations, as close as possible to the abstractions of the reference summaries. We evaluated our approach on two different datasets, with legal documents in English and French. Results show that our approach allows to reduce non-factual hallucinations and maximize both summary coverage and factual hallucinations at entity-level. Moreover, the overall quality of summaries is also improved, showing that guiding summarization with entities is a valuable solution for legal documents summarization.</abstract>
<identifier type="citekey">bendahman-etal-2025-hallucinations</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.275/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>5331</start>
<end>5344</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Not all Hallucinations are Good to Throw Away When it Comes to Legal Abstractive Summarization
%A Bendahman, Nihed
%A Pinel-Sauvagnat, Karen
%A Hubert, Gilles
%A Billami, Mokhtar Boumedyen
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F bendahman-etal-2025-hallucinations
%X Automatic summarization of legal documents requires a thorough understanding of their specificities, mainly with respect to the vocabulary used by legal experts. Indeed, the latter rely heavily on their external knowledge when writing summaries, in order to contextualize the main entities of the source document. This leads to reference summaries containing many abstractions, that sota models struggle to generate. In this paper, we propose an entity-driven approach aiming at learning the model to generate factual hallucinations, as close as possible to the abstractions of the reference summaries. We evaluated our approach on two different datasets, with legal documents in English and French. Results show that our approach allows to reduce non-factual hallucinations and maximize both summary coverage and factual hallucinations at entity-level. Moreover, the overall quality of summaries is also improved, showing that guiding summarization with entities is a valuable solution for legal documents summarization.
%U https://aclanthology.org/2025.naacl-long.275/
%P 5331-5344
Markdown (Informal)
[Not all Hallucinations are Good to Throw Away When it Comes to Legal Abstractive Summarization](https://aclanthology.org/2025.naacl-long.275/) (Bendahman et al., NAACL 2025)
ACL