5 papers
FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Risk
Tianyu Zhao, Mahmoud Srewa, Salma Elmalaki
Federated Learning (FL) inherently mitigates mass data centralization risks; however, its privacy protections are not equally distributed - leaving vulnerable individuals dispropor…
APPA: Adaptive Preference Pluralistic Alignment for Fair Federated RLHF of LLMs
Mahmoud Srewa, Tianyu Zhao, Salma Elmalaki
Aligning large language models (LLMs) with diverse human preferences requires pluralistic alignment, where a single model must respect the values of multiple distinct groups simult…
A Systematic Evaluation of Preference Aggregation in Federated RLHF for Pluralistic Alignment of LLMs
Mahmoud Srewa, Tianyu Zhao, Salma Elmalaki
This paper addresses the challenge of aligning large language models (LLMs) with diverse human preferences within federated learning (FL) environments, where standard methods often…
PluralLLM: Pluralistic Alignment in LLMs via Federated Learning
Mahmoud Srewa, Tianyu Zhao, Salma Elmalaki
Ensuring Large Language Models (LLMs) align with diverse human preferences while preserving privacy and fairness remains a challenge. Existing methods, such as Reinforcement Learni…
Towards Fairness-aware Crowd Management System and Surge Prevention in Smart Cities
Yixin Zhang, Tianyu Zhao, Salma Elmalaki
Instances of casualties resulting from large crowds persist, highlighting the existing limitations of current crowd management practices in Smart Cities. One notable drawback is th…