Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection

Jianfei He, Lilin Wang, Jiaying Wang, Zhenyu Liu, Hongbin Na, Zimu Wang, Wei Wang, Qi Chen*

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

Identifying offensive language is essential for maintaining safety and sustainability in the social media era. Though large language models (LLMs) have demonstrated encouraging potential in social media analytics, they lack thorough evaluation when in offensive language detection, particularly in multilingual environments. We for the first time evaluate multilingual offensive language detection of LLMs in three languages: English, Spanish, and German with three LLMs, GPT-3.5, Flan-T5, and Mistral, in both monolingual and multilingual settings. We further examine the impact of different prompt languages and augmented translation data for the task in non-English contexts. Furthermore, we discuss the impact of the inherent bias in LLMs and the datasets in the mispredictions related to sensitive topics.

Original languageEnglish
Title of host publicationProceedings - 2024 IEEE Smart World Congress, SWC 2024 - 2024 IEEE Ubiquitous Intelligence and Computing, Autonomous and Trusted Computing, Digital Twin, Metaverse, Privacy Computing and Data Security, Scalable Computing and Communications
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1603-1608
Number of pages6
ISBN (Electronic)9798331520861
DOIs
Publication statusPublished - 2024
Event10th IEEE Smart World Congress, SWC 2024 - Nadi, Fiji
Duration: 2 Dec 20247 Dec 2024

Publication series

NameProceedings - 2024 IEEE Smart World Congress, SWC 2024 - 2024 IEEE Ubiquitous Intelligence and Computing, Autonomous and Trusted Computing, Digital Twin, Metaverse, Privacy Computing and Data Security, Scalable Computing and Communications

Conference

Conference10th IEEE Smart World Congress, SWC 2024
Country/TerritoryFiji
CityNadi
Period2/12/247/12/24

Keywords

  • large language models
  • multilingual
  • Offensive language detection

Fingerprint

Dive into the research topics of 'Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection'. Together they form a unique fingerprint.

Cite this