Metraipolis › archive › dc_68443df11124
Used, Mentioned, or Condemned? A Controlled Contrast-Set Diagnostic for the Use-Mention Distinction in Code-Mixed Hinglish Misogyny Detection — arXiv:2609.22261
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22261
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:49:28.466Z
- SHA-256 of the archived text
72afed45103c30fc7d1e77b545039461f33641e5137d597e6f5de50197983748- Stable URL of this page
https://metraipolis.com/documento/dc_68443df11124
How to cite
Used, Mentioned, or Condemned? A Controlled Contrast-Set Diagnostic for the Use-Mention Distinction in Code-Mixed Hinglish Misogyny Detection — arXiv:2609.22261 — arXiv (en), https://arxiv.org/abs/2609.22261 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_68443df11124 (Metraipolis archive dc_68443df11124, sha256 72afed45103c30fc7d1e77b545039461f33641e5137d597e6f5de50197983748)
BibTeX
@misc{dc68443df11124,
title = {Used, Mentioned, or Condemned? A Controlled Contrast-Set Diagnostic for the Use-Mention Distinction in Code-Mixed Hinglish Misogyny Detection — arXiv:2609.22261},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22261},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_68443df11124; sha256 72afed45103c30fc7d1e77b545039461f33641e5137d597e6f5de50197983748},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22261. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Lexicon-driven misogyny detectors cannot, by construction, distinguish a slur used against a woman from the same slur mentioned in counter-speech ("don't call her that") -- yet exactly this distinction governs whether moderation protects or silences the people discussing abuse. We study this problem in code-mixed Hinglish and make three contributions. First, we diagnose two evaluation artifacts on a publicly available redacted corpus: category-encoding anonymization placeholders leak the label (a no-learning rule scores 1.000), and even after they are neutralized misogynistic and benign comments occupy lexically disjoint registers, so bag-of-words reaches macro-F1 approximately 1.00 under random cross-validation but collapses under template-disjoint evaluation. Second, we release Hinglish-MGY-Diag, a deterministic generator and a 416-item / 163-minimal-pair contrast-set diagnostic across five linguistically motivated categories in which slur presence and gendered register are decorrelated from the label by construction. Third, we introduce a strict pair-consistency metric that credits a model only when both members of a minimal pair are correctly labelled. Five from-scratch classical baselines evaluated under construction-disjoint five-fold cross-validation reveal that the strongest model reaches 0.93 accuracy on the cleanest use-mention subset but only 0.82 consistency -- it still mislabels roughly one counter-speech pair in five. A frontier LLM used as an author-model ceiling attains 1.000 on all metrics, doubling as independent label validation and confirming the benchmark is a capability gradient rather than an adversarial wall. We release all code, data, the generator, and an arms-length LLM harness for reproducing every number.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2609.22261 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:48:44.923Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).