5 papers
DeepBias: Adaptive In-depth Probing of Social Biases in LVLMs
Anqi Li, Jie Zhang, Zhongqi Wang +4
While Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities, they remain highly susceptible to embedded social biases. Existing bias evaluation protocols predomi…
Textual Data Bias Detection and Mitigation -- An Extensible Pipeline with Experimental Evaluation
Rebekka Görge, Sujan Sai Gannamaneni, Tabea Naeven +10
Textual data used to train large language models (LLMs) exhibits multifaceted bias manifestations encompassing harmful language and skewed demographic distributions. Regulations su…
Diverse Human Value Alignment for Large Language Models via Ethical Reasoning
Jiahao Wang, Songkai Xue, Jinghui Li +1
Ensuring that Large Language Models (LLMs) align with the diverse and evolving human values across different regions and cultures remains a critical challenge in AI ethics. Current…
Minimax Regret Learning for Data with Heterogeneous Subgroups
Weibin Mo, Weijing Tang, Songkai Xue +2
Modern complex datasets often consist of various sub-populations with known group information. In the presence of sub-population heterogeneity, it is crucial to develop robust and…
Distributionally Robust Performative Prediction
Songkai Xue, Yuekai Sun
Performative prediction aims to model scenarios where predictive outcomes subsequently influence the very systems they target. The pursuit of a performative optimum (PO) -- minimiz…