@inproceedings{dong-etal-2022-faithful,
title = "Faithful to the Document or to the World? Mitigating Hallucinations via Entity-Linked Knowledge in Abstractive Summarization",
author = "Dong, Yue and
Wieting, John and
Verga, Pat",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.76/",
doi = "10.18653/v1/2022.findings-emnlp.76",
pages = "1067--1082",
abstract = "Existing abstractive summarization systems are hampered by content hallucinations in which models generate text that is not directly inferable from the source alone. Annotations from prior work have shown that some of these hallucinations, while being {\textquoteleft}unfaithful' to the source, are nonetheless factual. Our analysis in this paper suggests that these factual hallucinations occur as a result of the prevalence of factual yet unfaithful entities in summarization datasets. We find that these entities are not aberrations, but instead examples of additional world knowledge being readily used to latently connect entities and concepts {--} in this case connecting entities in the source document to those in the target summary. In our analysis and experiments, we demonstrate that connecting entities to an external knowledge base can lend provenance to many of these unfaithful yet factual entities, and further, this knowledge can be used to improve the factuality of summaries without simply making them more extractive."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dong-etal-2022-faithful">
<titleInfo>
<title>Faithful to the Document or to the World? Mitigating Hallucinations via Entity-Linked Knowledge in Abstractive Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Wieting</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pat</namePart>
<namePart type="family">Verga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing abstractive summarization systems are hampered by content hallucinations in which models generate text that is not directly inferable from the source alone. Annotations from prior work have shown that some of these hallucinations, while being ‘unfaithful’ to the source, are nonetheless factual. Our analysis in this paper suggests that these factual hallucinations occur as a result of the prevalence of factual yet unfaithful entities in summarization datasets. We find that these entities are not aberrations, but instead examples of additional world knowledge being readily used to latently connect entities and concepts – in this case connecting entities in the source document to those in the target summary. In our analysis and experiments, we demonstrate that connecting entities to an external knowledge base can lend provenance to many of these unfaithful yet factual entities, and further, this knowledge can be used to improve the factuality of summaries without simply making them more extractive.</abstract>
<identifier type="citekey">dong-etal-2022-faithful</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.76</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.76/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>1067</start>
<end>1082</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Faithful to the Document or to the World? Mitigating Hallucinations via Entity-Linked Knowledge in Abstractive Summarization
%A Dong, Yue
%A Wieting, John
%A Verga, Pat
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F dong-etal-2022-faithful
%X Existing abstractive summarization systems are hampered by content hallucinations in which models generate text that is not directly inferable from the source alone. Annotations from prior work have shown that some of these hallucinations, while being ‘unfaithful’ to the source, are nonetheless factual. Our analysis in this paper suggests that these factual hallucinations occur as a result of the prevalence of factual yet unfaithful entities in summarization datasets. We find that these entities are not aberrations, but instead examples of additional world knowledge being readily used to latently connect entities and concepts – in this case connecting entities in the source document to those in the target summary. In our analysis and experiments, we demonstrate that connecting entities to an external knowledge base can lend provenance to many of these unfaithful yet factual entities, and further, this knowledge can be used to improve the factuality of summaries without simply making them more extractive.
%R 10.18653/v1/2022.findings-emnlp.76
%U https://aclanthology.org/2022.findings-emnlp.76/
%U https://doi.org/10.18653/v1/2022.findings-emnlp.76
%P 1067-1082
Markdown (Informal)
[Faithful to the Document or to the World? Mitigating Hallucinations via Entity-Linked Knowledge in Abstractive Summarization](https://aclanthology.org/2022.findings-emnlp.76/) (Dong et al., Findings 2022)
ACL