arXiv subjects

Anam Zahid

Publications and source records attributed to Anam Zahid.

4 recordsLinked to original sources

arXiv2025

FairUDT: Fairness-aware Uplift Decision Trees

Training data used for developing machine learning classifiers can exhibit biases against specific protected attributes. Such biases typically originate from historical discrimination or certain underlying patterns that disproportionately under-represent minority groups, such as those identified by their gender, religion, or race. In this paper, we propose a novel approach, FairUDT, a fairness-aware Uplift-based Decision Tree for discrimination identification. FairUDT demonstrates how the integration of uplift modeling with decision trees can be adapted to include fair splitting criteria. Additionally, we introduce a modified leaf relabeling approach for removing discrimination. We divide our dataset into favored and deprived groups based on a binary sensitive attribute, with the favored dataset serving as the treatment group and the deprived dataset as the control group. By applying FairUDT and our leaf relabeling approach to preprocess three benchmark datasets, we achieve an acceptable accuracy-discrimination tradeoff. We also show that FairUDT is inherently interpretable and can be utilized in discrimination detection tasks. The code for this project is available https://github.com/ara-25/FairUDT

cs.LG↗

arXiv2025

Who is Responsible? The Data, Models, Users or Regulations? A Comprehensive Survey on Responsible Generative AI for a Sustainable Future

Generative AI is rapidly moving from research to deployment, elevating the need for responsible development, evaluation, and governance. We conduct a PRISMA guided review of 232 studies (November 2022 - December 2025), spanning large language models, vision language models, diffusion models, and agentic pipelines. We make four contributions: (1) the first survey bridging governance principles, technical evaluation, and domain deployment across all four system types; (2) a ten-criterion rubric (C1-C10) scoring major AI safety benchmarks on risk-surface coverage, paired with a policy crosswalk mapping benchmarks to regulatory requirements; (3) twelve lifecycle KPIs, explainability guidance for foundation models, and a testbed catalogue; and (4) domain-specific analysis across healthcare, finance, education, arts, agriculture, and defense. Three findings emerge: benchmark coverage is dense for bias and toxicity but sparse for privacy, provenance, deepfakes, and system-level failures in agentic settings; evaluations remain largely static and task local, limiting audit portability; and inconsistent documentation complicates cross-release comparison. We outline a research agenda prioritizing adaptive multimodal evaluation, privacy and provenance testing, deepfake risk assessment, calibration reporting, versioned artifacts, and continuous monitoring. This survey offers a structured path to align generative AI evaluation with governance needs for safe and accountable deployment.

cs.CY↗

arXiv2024

ViLBias: Detecting and Reasoning about Bias in Multimodal Content

Detecting bias in multimodal news requires models that reason over text--image pairs, not just classify text. In response, we present ViLBias, a VQA-style benchmark and framework for detecting and reasoning about bias in multimodal news. The dataset comprises 40,945 text--image pairs from diverse outlets, each annotated with a bias label and concise rationale using a two-stage LLM-as-annotator pipeline with hierarchical majority voting and human-in-the-loop validation. We evaluate Small Language Models (SLMs), Large Language Models (LLMs), and Vision--Language Models (VLMs) across closed-ended classification and open-ended reasoning (oVQA), and compare parameter-efficient tuning strategies. Results show that incorporating images alongside text improves detection accuracy by 3--5\%, and that LLMs/VLMs better capture subtle framing and text--image inconsistencies than SLMs. Parameter-efficient methods (LoRA/QLoRA/Adapters) recover 97--99\% of full fine-tuning performance with $<5\%$ trainable parameters. For oVQA, reasoning accuracy spans 52--79\% and faithfulness 68--89\%, both improved by instruction tuning; closed accuracy correlates strongly with reasoning ($r = 0.91$). ViLBias offers a scalable benchmark and strong baselines for multimodal bias detection and rationale quality.

cs.AI↗

arXiv2021

Emergency Department Optimization and Load Prediction in Hospitals

Over the past several years, across the globe, there has been an increase in people seeking care in emergency departments (EDs). ED resources, including nurse staffing, are strained by such increases in patient volume. Accurate forecasting of incoming patient volume in emergency departments (ED) is crucial for efficient utilization and allocation of ED resources. Working with a suburban ED in the Pacific Northwest, we developed a tool powered by machine learning models, to forecast ED arrivals and ED patient volume to assist end-users, such as ED nurses, in resource allocation. In this paper, we discuss the results from our predictive models, the challenges, and the learnings from users' experiences with the tool in active clinical deployment in a real world setting.

cs.LG↗