ALTO：非洲与黎凡特地区技术辅助性别暴力语料库

View PDF

Abstract:Tech-facilitated gender based violence (TFGBV) is a pervasive online harm affecting women and gender minority groups through its many direct and covert forms. Current models and annotated datasets for gendered harm detection are dominated by data from, and models trained in, Global North languages. In collaboration with civil society organizations (CSOs) from Jordan, Francophone West Africa, and Kenya, we developed a community-led approach to crowdsource culturally and linguistically relevant instances of TFGBV in Levantine Arabic, African French, and Swahili. We annotated the crowdsourced data using active learning to develop a small but performant dataset (N=3022) called ALTO to improve TFGBV detection in the three languages. Through benchmarking and fine-tuning experiments, we show that existing harmful content detection models show poor TFGBV recall within ALTO and improve with fine-tuning. We found that models often miss covert harms across all languages, while error rates are markedly higher in Swahili. We report the experimental results and release the annotation taxonomy, dataset, and trained models.

Comments:	8 pages main body, 10 pages appendix, 1 figure
Subjects:	Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG)
ACM classes:	I.2.7; K.4.2
Cite as:	arXiv:2611.06706 [cs.CL]
	(or arXiv:2611.06706v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2611.06706 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Tianwei (Terry) Zhang [view email]
[v1] Wed, 4 Nov 2026 16:06:15 UTC (178 KB)