4 papers
The Confidence Trap: Gender Bias and Predictive Certainty in LLMs
Ahmed Sabir, Markus Kängsepp, Rajesh Sharma
The increased use of Large Language Models (LLMs) in sensitive domains leads to growing interest in how their confidence scores correspond to fairness and bias. This study examines…
Exploring Gender Bias Beyond Occupational Titles
Ahmed Sabir, Rajesh Sharma
In this work, we investigate the correlation between gender and contextual biases, focusing on elements such as action verbs, object nouns, and particularly on occupations. We intr…
Contrasting Cognitive Styles in Vision-Language Models: Holistic Attention in Japanese Versus Analytical Focus in English
Ahmed Sabir, AzinoviÄ Gasper, Mengsay Loem +1
Cross-cultural research in perception and cognition has shown that individuals from different cultural backgrounds process visual information in distinct ways. East Asians, for exa…
How Effectively Do LLMs Extract Feature-Sentiment Pairs from App Reviews?
Faiz Ali Shah, Ahmed Sabir, Rajesh Sharma +1
Automatic analysis of user reviews to understand user sentiments toward app functionality (i.e. app features) helps align development efforts with user expectations and needs. Rece…