LifeTox: Unveiling Implicit Toxicity in Life Advice

Minbeom Kim, Jahyun Koo, Hwanhee Lee, Joonsuk Park, Hwaran Lee, Kyomin Jung


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.
Anthology ID:
2024.naacl-short.60
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
688–698
Language:
URL:
https://aclanthology.org/2024.naacl-short.60
DOI:
Bibkey:
Cite (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.
Cite (Informal):
LifeTox: Unveiling Implicit Toxicity in Life Advice (Kim et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-short.60.pdf