{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T21:11:32Z","timestamp":1771967492362,"version":"3.50.1"},"reference-count":0,"publisher":"TechForum Publishing Group","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bull. Comput. Data Sci."],"published-print":{"date-parts":[[2024,12,30]]},"abstract":"<jats:p>Automatic social bias detection is increasingly deployed to moderate harmful content on social media, often in settings where training data for low-resource languages is scarce. Recent work shows that multilingual transformers fine-tuned on high-resource languages can be adapted to detect biased content in Hindi with strong overall F1 scores. However, little is known about how such cross-lingual bias detectors behave across different social groups: do they protect all communities equally, or do some groups experience systematically higher false positives or false negatives? In this paper, we present a group-level fairness analysis of cross-lingual social bias detection for Hindi. Building on a Hindi social bias dataset annotated with bias labels, categories (e.g., religion, politics, caste, occupation), targets, and sentiment, we derive a set of group indicators for religious communities, political actors, and caste-related mentions. We then compare several training regimes for XLM-R: (i) Hindi-only training, (ii) sequential English\u2192Hindi fine-tuning, (iii) joint English+Hindi training, and (iv) a translate-to-English pipeline. For each setup, we report both global metrics and group-wise error rates (true positive rate, false positive rate, false negative rate) and summarize disparities via worst-group F1 and average absolute gap. Our analysis reveals three key findings. First, cross-lingual transfer that improves overall F1 may increase error disparities for specific communities, especially minority or politically sensitive groups. Second, translate-to-English pipelines systematically over-flag some religious and political groups compared to native-script models. Third, a simple group-aware reweighting scheme can substantially reduce worst-group error without sacrificing average performance. We conclude with recommendations for evaluating and mitigating unfairness when deploying cross-lingual bias detectors in Hindi and other low-resource languages.<\/jats:p>","DOI":"10.71448\/bcds2452-1","type":"journal-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:45:39Z","timestamp":1771965939000},"page":"1-13","source":"Crossref","is-referenced-by-count":0,"title":["Who Gets Protected? A Fairness Analysis of Cross-Lingual Social Bias Detection for Hindi"],"prefix":"10.71448","volume":"5","author":[{"name":"Indian Institute of Technology (IIT) Delhi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sonia","family":"Shahzadi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanjiv","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"name":"Indian Institute of Technology (IIT) Delhi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"52394","published-online":{"date-parts":[[2024,12,30]]},"container-title":["Bulletin of Computer and Data Sciences"],"original-title":[],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:45:40Z","timestamp":1771965940000},"score":1,"resource":{"primary":{"URL":"https:\/\/bcds.ch\/who-gets-protected-a-fairness-analysis-of-cross-lingual-social-bias-detection-for-hindi\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,30]]},"references-count":0,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,12,30]]},"published-print":{"date-parts":[[2024,12,30]]}},"URL":"https:\/\/doi.org\/10.71448\/bcds2452-1","relation":{},"ISSN":["3072-2926"],"issn-type":[{"value":"3072-2926","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,30]]}}}