Annotation Matters: Resolving Cross-Corpus Performance Drops in Hebrew Offensive Language Detection

Gili Berger Hefetz, Yossef Haim Shrem, Natalia Vanetik, Chaya Liebeskind


Abstract
Cross-dataset generalization remains a major challenge in offensive language detection, especially for culturally sensitive languages such as Hebrew. A large Hebrew dataset introduced in prior work (citation omitted for double-blind review) was annotated via a taxonomy-grounded, prompt-guided LLM protocol and achieved strong in-domain results. However, performance degraded sharply on two external Hebrew corpora. We investigate whether this degradation reflects domain shift or annotation shift, i.e., differences in how offensiveness is operationalized across datasets. Using the same prompt framework and a dual-LLM agreement procedure, we re-annotate both external corpora and quantify label divergence. We observe substantial mismatch between the original and new annotations, consistent with the view that offensiveness is not objective but depends on cultural context, discourse conventions, political framing, and the interpretation of irony. Evaluating models against the new labels yields markedly improved performance, and fine-tuning with the new external labels further improves results. Overall, our findings suggest that cross-dataset failure in affective NLP tasks may often be driven by annotation mismatch rather than domain adaptation limitations, highlighting the importance of annotation validity and culturally grounded labeling protocols.
Anthology ID:
2026.cas-1.10
Volume:
Proceedings of Computational Affective Science (CAS) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Christopher Bagdon, Krishnapriya Vishnubhotla, Kristen A. Lindquist, Lyle Ungar, Roman Klinger, Saif M. Mohammad
Venues:
CAS | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
116–124
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-cas-10
DOI:
10.63317/3fss6oc5mono
Bibkey:
Cite (ACL):
Gili Berger Hefetz, Yossef Haim Shrem, Natalia Vanetik, and Chaya Liebeskind. 2026. Annotation Matters: Resolving Cross-Corpus Performance Drops in Hebrew Offensive Language Detection. In Proceedings of Computational Affective Science (CAS) @ LREC 2026, pages 116–124, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Annotation Matters: Resolving Cross-Corpus Performance Drops in Hebrew Offensive Language Detection (Berger Hefetz et al., CAS 2026)
Copy Citation: