@inproceedings{nozza-etal-2022-measuring,
title = "Measuring Harmful Sentence Completion in Language Models for {LGBTQIA}+ Individuals",
author = "Nozza, Debora and
Bianchi, Federico and
Lauscher, Anne and
Hovy, Dirk",
editor = "Chakravarthi, Bharathi Raja and
Bharathi, B and
McCrae, John P and
Zarrouk, Manel and
Bali, Kalika and
Buitelaar, Paul",
booktitle = "Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.ltedi-1.4",
doi = "10.18653/v1/2022.ltedi-1.4",
pages = "26--34",
abstract = "Current language technology is ubiquitous and directly influences individuals{'} lives worldwide. Given the recent trend in AI on training and constantly releasing new and powerful large language models (LLMs), there is a need to assess their biases and potential concrete consequences. While some studies have highlighted the shortcomings of these models, there is only little on the negative impact of LLMs on LGBTQIA+ individuals. In this paper, we investigated a state-of-the-art template-based approach for measuring the harmfulness of English LLMs sentence completion when the subjects belong to the LGBTQIA+ community. Our findings show that, on average, the most likely LLM-generated completion is an identity attack 13{\%} of the time. Our results raise serious concerns about the applicability of these models in production environments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nozza-etal-2022-measuring">
<titleInfo>
<title>Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals</title>
</titleInfo>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Bianchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Lauscher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">B</namePart>
<namePart type="family">Bharathi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manel</namePart>
<namePart type="family">Zarrouk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Buitelaar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current language technology is ubiquitous and directly influences individuals’ lives worldwide. Given the recent trend in AI on training and constantly releasing new and powerful large language models (LLMs), there is a need to assess their biases and potential concrete consequences. While some studies have highlighted the shortcomings of these models, there is only little on the negative impact of LLMs on LGBTQIA+ individuals. In this paper, we investigated a state-of-the-art template-based approach for measuring the harmfulness of English LLMs sentence completion when the subjects belong to the LGBTQIA+ community. Our findings show that, on average, the most likely LLM-generated completion is an identity attack 13% of the time. Our results raise serious concerns about the applicability of these models in production environments.</abstract>
<identifier type="citekey">nozza-etal-2022-measuring</identifier>
<identifier type="doi">10.18653/v1/2022.ltedi-1.4</identifier>
<location>
<url>https://aclanthology.org/2022.ltedi-1.4</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>26</start>
<end>34</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals
%A Nozza, Debora
%A Bianchi, Federico
%A Lauscher, Anne
%A Hovy, Dirk
%Y Chakravarthi, Bharathi Raja
%Y Bharathi, B.
%Y McCrae, John P.
%Y Zarrouk, Manel
%Y Bali, Kalika
%Y Buitelaar, Paul
%S Proceedings of the Second Workshop on Language Technology for Equality, Diversity and Inclusion
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F nozza-etal-2022-measuring
%X Current language technology is ubiquitous and directly influences individuals’ lives worldwide. Given the recent trend in AI on training and constantly releasing new and powerful large language models (LLMs), there is a need to assess their biases and potential concrete consequences. While some studies have highlighted the shortcomings of these models, there is only little on the negative impact of LLMs on LGBTQIA+ individuals. In this paper, we investigated a state-of-the-art template-based approach for measuring the harmfulness of English LLMs sentence completion when the subjects belong to the LGBTQIA+ community. Our findings show that, on average, the most likely LLM-generated completion is an identity attack 13% of the time. Our results raise serious concerns about the applicability of these models in production environments.
%R 10.18653/v1/2022.ltedi-1.4
%U https://aclanthology.org/2022.ltedi-1.4
%U https://doi.org/10.18653/v1/2022.ltedi-1.4
%P 26-34
Markdown (Informal)
[Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals](https://aclanthology.org/2022.ltedi-1.4) (Nozza et al., LTEDI 2022)
ACL