@inproceedings{galeshchuk-2024-entity,
title = "Entity Embellishment Mitigation in {LLM}s Output with Noisy Synthetic Dataset for Alignment",
author = "Galeshchuk, Svitlana",
editor = "Romanyshyn, Mariana and
Romanyshyn, Nataliia and
Hlybovets, Andrii and
Ignatenko, Oleksii",
booktitle = "Proceedings of the Third Ukrainian Natural Language Processing Workshop (UNLP) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.unlp-1.15",
pages = "129--134",
abstract = "The present work focuses on the entity embellishments when named entities are accompanied by additional information that is not supported by the context or the source material. Our paper contributes into mitigating this problem in large language model{'}s generated texts, summaries in particular, by proposing the approach with synthetic noise injection in the generated samples that are further used for alignment of finetuned LLM. We also challenge the issue of solutions scarcity for low-resourced languages and test our approach with corpora in Ukrainian.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="galeshchuk-2024-entity">
<titleInfo>
<title>Entity Embellishment Mitigation in LLMs Output with Noisy Synthetic Dataset for Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svitlana</namePart>
<namePart type="family">Galeshchuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Ukrainian Natural Language Processing Workshop (UNLP) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Romanyshyn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nataliia</namePart>
<namePart type="family">Romanyshyn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrii</namePart>
<namePart type="family">Hlybovets</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oleksii</namePart>
<namePart type="family">Ignatenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The present work focuses on the entity embellishments when named entities are accompanied by additional information that is not supported by the context or the source material. Our paper contributes into mitigating this problem in large language model’s generated texts, summaries in particular, by proposing the approach with synthetic noise injection in the generated samples that are further used for alignment of finetuned LLM. We also challenge the issue of solutions scarcity for low-resourced languages and test our approach with corpora in Ukrainian.</abstract>
<identifier type="citekey">galeshchuk-2024-entity</identifier>
<location>
<url>https://aclanthology.org/2024.unlp-1.15</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>129</start>
<end>134</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Entity Embellishment Mitigation in LLMs Output with Noisy Synthetic Dataset for Alignment
%A Galeshchuk, Svitlana
%Y Romanyshyn, Mariana
%Y Romanyshyn, Nataliia
%Y Hlybovets, Andrii
%Y Ignatenko, Oleksii
%S Proceedings of the Third Ukrainian Natural Language Processing Workshop (UNLP) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F galeshchuk-2024-entity
%X The present work focuses on the entity embellishments when named entities are accompanied by additional information that is not supported by the context or the source material. Our paper contributes into mitigating this problem in large language model’s generated texts, summaries in particular, by proposing the approach with synthetic noise injection in the generated samples that are further used for alignment of finetuned LLM. We also challenge the issue of solutions scarcity for low-resourced languages and test our approach with corpora in Ukrainian.
%U https://aclanthology.org/2024.unlp-1.15
%P 129-134
Markdown (Informal)
[Entity Embellishment Mitigation in LLMs Output with Noisy Synthetic Dataset for Alignment](https://aclanthology.org/2024.unlp-1.15) (Galeshchuk, UNLP 2024)
ACL