Adding a brief, hand-written video context improved LLM toxicity detection in Serbian, Croatian, and Bosnian, raising F1 scores by up to 0.10 across four models.
Data-efficient strategies for expanding hate speech detection into under-resourced languages,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages
Adding a brief, hand-written video context improved LLM toxicity detection in Serbian, Croatian, and Bosnian, raising F1 scores by up to 0.10 across four models.