activity
20192025
most citedA review of clustering models in educational data science towards fairness-aware learning

26 citations · 86 across the 28 of their papers we have counts for

collaborators
Showing 2024Show all

10 papers · 1 filter

cs.CR2024

Emerging Security Challenges of Large Language Models

Herve Debar, Sven Dietrich, Pavel Laskov +2

Large language models (LLMs) have achieved record adoption in a short period of time across many different sectors including high importance areas such as education [4] and healthc…

eess.SY2024

Shape error prediction in 5-axis machining using graph neural networks

Julia Huuk, Abheek Dhingra, Eirini Ntoutsi +1

This paper presents an innovative method for predicting shape errors in 5-axis machining using graph neural networks. The graph structure is defined with nodes representing workpie…

cs.CL2024

Unlocking LLMs: Addressing Scarce Data and Bias Challenges in Mental Health

Vivek Kumar, Eirini Ntoutsi, Pushpraj Singh Rajawat +2

Large language models (LLMs) have shown promising capabilities in healthcare analysis but face several challenges like hallucinations, parroting, and bias manifestation. These chal…

cs.CL2024

Transparent Neighborhood Approximation for Text Classifier Explanation

Yi Cai, Arthur Zimek, Eirini Ntoutsi +1

Recent literature highlights the critical role of neighborhood construction in deriving model-agnostic explanations, with a growing trend toward deploying generative models to impr…

cs.CY2024

Fairness Evaluation with Item Response Theory

Ziqi Xu, Sevvandi Kandanaarachchi, Cheng Soon Ong +1

Item Response Theory (IRT) has been widely used in educational psychometrics to assess student ability, as well as the difficulty and discrimination of test questions. In this cont…

cs.LG2024

Adversarial Robustness of VAEs across Intersectional Subgroups

Chethan Krishnamurthy Ramanaik, Arjun Roy, Eirini Ntoutsi

Despite advancements in Autoencoders (AEs) for tasks like dimensionality reduction, representation learning and data generation, they remain vulnerable to adversarial attacks. Vari…