@inproceedings{bibcite_16157,
  author = {Anna Zawadzka and Przemys{\l}aw G{\l}omb},
  title = {Architecture Matters: Gender Disparities in Automated Image Moderation},
  abstract = {<p>Automated image moderation systems shape online visibility and dataset curation, yet prior work has identified demographic disparities in similarity-based NSFW classifiers. We compare such systems with instruction-tuned vision-language models (VLMs) that generate structured moderation decisions with textual rationales. Using the PHASE-annotated subset of the GCC dataset, \&nbsp;we compute false positive rates overall and by gender.\&nbsp;<br>Results show substantial variation in moderation strictness and in bias direction: two models show more pronounced strictness in moderation of male images, while other two exhibit higher removal rates for female images.\&nbsp;<br>Reasoning-based models do not consistently mitigate bias but, in the proposed pipeline, they offer a transparency layer.</p>},
  year = {2026},
  journal = {PP-RAI{\textquoteright}2026: 7th Polish Conference on Artificial Intelligence},
  month = {04/2026},
}