EUVIMEDEUVIMED entdecken
Crossref

How Reasoning Influences Intersectional Biases in Vision–Language Models (Student Abstract)

Adit Desai, Sudipta Roy, Mohna Chakraborty

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41185-41187

DOI: 10.1609/aaai.v40i48.42208 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Adit Desai und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vision-Language Models (VLMs) are increasingly deployed across downstream tasks, yet their training data often encode social biases that surface in outputs. Unlike humans, who interpret images through contextual and social cues, VLMs process them through statistical associations, often leading to reasoning that diverges from human reasoning. By analyzing how a VLM reasons, we can understand how inherent biases are perpetuated and can adversely affect downstream performance. To examine this gap, we systematically analyze social biases in five open-source VLMs for an occupation prediction task, on the FairFace dataset. Across 32 occupations and three different prompting styles, we elicit both predictions and reasoning. Our findings show that the biased reasoning patterns systematically underlie intersectional disparities, highlighting the need to align VLM reasoning with human values before downstream deployment.

Zitieren

APA

Desai, A., Roy, S., & Chakraborty, M. (2026). How Reasoning Influences Intersectional Biases in Vision–Language Models (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41185-41187. https://doi.org/10.1609/aaai.v40i48.42208

Vancouver

Desai A, Roy S, Chakraborty M. How Reasoning Influences Intersectional Biases in Vision–Language Models (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41185-41187. doi:10.1609/aaai.v40i48.42208

BibTeX
@article{Desai2026,
  author = {Desai, Adit and Roy, Sudipta and Chakraborty, Mohna},
  title = {How Reasoning Influences Intersectional Biases in Vision–Language Models (Student Abstract)},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {48},
  pages = {41185--41187},
  doi = {10.1609/aaai.v40i48.42208}
}
Kostenlos starten →