@inproceedings{kim-etal-2024-lifetox,
title = "{L}ife{T}ox: Unveiling Implicit Toxicity in Life Advice",
author = "Kim, Minbeom and
Koo, Jahyun and
Lee, Hwanhee and
Park, Joonsuk and
Lee, Hwaran and
Jung, Kyomin",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-short.60/",
doi = "10.18653/v1/2024.naacl-short.60",
pages = "688--698",
abstract = "As large language models become increasingly integrated into daily life, detecting implicit toxicity across diverse contexts is crucial. To this end, we introduce $\texttt{LifeTox}$, a dataset designed for identifying implicit toxicity within a broad range of advice-seeking scenarios. Unlike existing safety datasets, $\texttt{LifeTox}$ comprises diverse contexts derived from personal experiences through open-ended questions. Our experiments demonstrate that RoBERTa fine-tuned on $\texttt{LifeTox}$ matches or surpasses the zero-shot performance of large language models in toxicity classification tasks. These results underscore the efficacy of $\texttt{LifeTox}$ in addressing the complex challenges inherent in implicit toxicity. We open-sourced the dataset and the $\texttt{LifeTox}$ moderator family; 350M, 7B, and 13B."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2024-lifetox">
<titleInfo>
<title>LifeTox: Unveiling Implicit Toxicity in Life Advice</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minbeom</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jahyun</namePart>
<namePart type="family">Koo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hwanhee</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joonsuk</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hwaran</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyomin</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As large language models become increasingly integrated into daily life, detecting implicit toxicity across diverse contexts is crucial. To this end, we introduce LifeTox, a dataset designed for identifying implicit toxicity within a broad range of advice-seeking scenarios. Unlike existing safety datasets, LifeTox comprises diverse contexts derived from personal experiences through open-ended questions. Our experiments demonstrate that RoBERTa fine-tuned on LifeTox matches or surpasses the zero-shot performance of large language models in toxicity classification tasks. These results underscore the efficacy of LifeTox in addressing the complex challenges inherent in implicit toxicity. We open-sourced the dataset and the LifeTox moderator family; 350M, 7B, and 13B.</abstract>
<identifier type="citekey">kim-etal-2024-lifetox</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-short.60</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-short.60/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>688</start>
<end>698</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LifeTox: Unveiling Implicit Toxicity in Life Advice
%A Kim, Minbeom
%A Koo, Jahyun
%A Lee, Hwanhee
%A Park, Joonsuk
%A Lee, Hwaran
%A Jung, Kyomin
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F kim-etal-2024-lifetox
%X As large language models become increasingly integrated into daily life, detecting implicit toxicity across diverse contexts is crucial. To this end, we introduce LifeTox, a dataset designed for identifying implicit toxicity within a broad range of advice-seeking scenarios. Unlike existing safety datasets, LifeTox comprises diverse contexts derived from personal experiences through open-ended questions. Our experiments demonstrate that RoBERTa fine-tuned on LifeTox matches or surpasses the zero-shot performance of large language models in toxicity classification tasks. These results underscore the efficacy of LifeTox in addressing the complex challenges inherent in implicit toxicity. We open-sourced the dataset and the LifeTox moderator family; 350M, 7B, and 13B.
%R 10.18653/v1/2024.naacl-short.60
%U https://aclanthology.org/2024.naacl-short.60/
%U https://doi.org/10.18653/v1/2024.naacl-short.60
%P 688-698
Markdown (Informal)
[LifeTox: Unveiling Implicit Toxicity in Life Advice](https://aclanthology.org/2024.naacl-short.60/) (Kim et al., NAACL 2024)
ACL
- Minbeom Kim, Jahyun Koo, Hwanhee Lee, Joonsuk Park, Hwaran Lee, and Kyomin Jung. 2024. LifeTox: Unveiling Implicit Toxicity in Life Advice. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 688–698, Mexico City, Mexico. Association for Computational Linguistics.