5 papers
IndicFairFace: Balanced Indian Face Dataset for Auditing and Mitigating Geographical Bias in Vision-Language Models
Aarish Shah Mohsin, Mohammed Tayyab Ilyas Khan, Mohammad Nadeem +3
Vision-Language Models (VLMs) are known to inherit and amplify societal biases from their web-scale training data with Indian being particularly misrepresented. Existing fairness-a…
Surgeons Are Indian Males and Speech Therapists Are White Females: Auditing Biases in Vision-Language Models for Healthcare Professionals
Zohaib Hasan Siddiqui, Dayam Nadeem, Mohammad Masudur Rahman +3
Vision language models (VLMs), such as CLIP and OpenCLIP, can encode and reflect stereotypical associations between medical professions and demographic attributes learned from web-…
Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages
Gulfarogh Azam, Mohd Sadique, Saif Ali +4
Transliteration, the process of mapping text from one script to another, plays a crucial role in multilingual natural language processing, especially within linguistically diverse…
Owls are wise and foxes are unfaithful: Uncovering animal stereotypes in vision-language models
Tabinda Aman, Mohammad Nadeem, Shahab Saquib Sohail +2
Animal stereotypes are deeply embedded in human culture and language. They often shape our perceptions and expectations of various species. Our study investigates how animal stereo…
Gender Bias in Text-to-Video Generation Models: A case study of Sora
Mohammad Nadeem, Shahab Saquib Sohail, Erik Cambria +2
The advent of text-to-video generation models has revolutionized content creation as it produces high-quality videos from textual prompts. However, concerns regarding inherent bias…