Nuria Oliver
YOU?
Author Swipe
View article: Beauty and the Bias: Exploring the Impact of Attractiveness on Multimodal Large Language Models
Beauty and the Bias: Exploring the Impact of Attractiveness on Multimodal Large Language Models Open
Physical attractiveness matters. It has been shown to influence human perception and decision-making, often leading to biased judgments that favor those deemed attractive in what is referred to as the "attractiveness halo effect". While ex…
View article: Between Help and Harm: An Evaluation of Mental Health Crisis Handling by LLMs
Between Help and Harm: An Evaluation of Mental Health Crisis Handling by LLMs Open
Large language model-powered chatbots have transformed how people seek information, especially in high-stakes contexts like mental health. Despite their support capabilities, safe detection and response to crises such as suicidal ideation …
View article: Towards Human-AI Complementarity in Matching Tasks
Towards Human-AI Complementarity in Matching Tasks Open
Data-driven algorithmic matching systems promise to help human decision makers make better matching decisions in a wide variety of high-stakes application domains, such as healthcare and social service provision. However, existing systems …
View article: Filters of Identity: AR Beauty and the Algorithmic Politics of the Digital Body
Filters of Identity: AR Beauty and the Algorithmic Politics of the Digital Body Open
This position paper situates AR beauty filters within the broader debate on Body Politics in HCI. We argue that these filters are not neutral tools but technologies of governance that reinforce racialized, gendered, and ableist beauty stan…
View article: ELLIS Alicante at CQs-Gen 2025: Winning the critical thinking questions shared task: LLM-based question generation and selection
ELLIS Alicante at CQs-Gen 2025: Winning the critical thinking questions shared task: LLM-based question generation and selection Open
The widespread adoption of chat interfaces based on Large Language Models (LLMs) raises concerns about promoting superficial learning and undermining the development of critical thinking skills. Instead of relying on LLMs purely for retrie…
View article: Beauty and the Bias: Exploring the Impact of Attractiveness on Multimodal Large Language Models
Beauty and the Bias: Exploring the Impact of Attractiveness on Multimodal Large Language Models Open
Physical attractiveness matters. It has been shown to influence human perception and decision-making, often leading to biased judgments that favor those deemed attractive in what is referred to as the "attractiveness halo effect". While ex…
View article: FedDiverse: Tackling Data Heterogeneity in Federated Learning with Diversity-Driven Client Selection
FedDiverse: Tackling Data Heterogeneity in Federated Learning with Diversity-Driven Client Selection Open
Federated Learning (FL) enables decentralized training of machine learning models on distributed data while preserving privacy. However, in real-world FL settings, client data is often non-identically distributed and imbalanced, resulting …
View article: Big Mobile Data for Social Good
Big Mobile Data for Social Good Open
In this chapter, I will illustrate the value of Big Data—particularly the data captured by the mobile network infrastructure—for Social Good by describing two projects in two different areas and regions of the world: natural disasters and …
View article: International AI Safety Report
International AI Safety Report Open
The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems. The report was mandated by the nations attending the AI Safety Summit in Bletchley, UK…
View article: Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated Learning
Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated Learning Open
Federated Learning (FL) has been proposed as a privacy-preserving solution for distributed machine learning, particularly in heterogeneous FL settings where clients have varying computational capabilities and thus train models with differe…
View article: Local vs distributed representations: What is the right basis for interpretability?
Local vs distributed representations: What is the right basis for interpretability? Open
Much of the research on the interpretability of deep neural networks has focused on studying the visual features that maximally activate individual neurons. However, recent work has cast doubts on the usefulness of such local representatio…
View article: What is beautiful is still good: the attractiveness halo effect in the era of beauty filters
What is beautiful is still good: the attractiveness halo effect in the era of beauty filters Open
The impact of cognitive biases on decision-making in the digital world remains under-explored despite its well-documented effects in physical contexts. This paper addresses this gap by investigating the attractiveness halo effect using AI-…
View article: The Disparate Benefits of Deep Ensembles
The Disparate Benefits of Deep Ensembles Open
Ensembles of Deep Neural Networks, Deep Ensembles, are widely used as a simple way to boost predictive performance. However, their impact on algorithmic fairness is not well understood yet. Algorithmic fairness examines how a model's perfo…
View article: An Art-centric perspective on AI-based content moderation of nudity
An Art-centric perspective on AI-based content moderation of nudity Open
At a time when the influence of generative Artificial Intelligence on visual arts is a highly debated topic, we raise the attention towards a more subtle phenomenon: the algorithmic censorship of artistic nudity online. We analyze the perf…
View article: Exploring the Boundaries of Content Moderation in Text-to-Image Generation
Exploring the Boundaries of Content Moderation in Text-to-Image Generation Open
This paper analyzes the community safety guidelines of five text-to-image (T2I) generation platforms and audits five T2I models, focusing on prompts related to the representation of humans in areas that might lead to societal stigma. While…
View article: Lookism: The overlooked bias in computer vision
Lookism: The overlooked bias in computer vision Open
In recent years, there have been significant advancements in computer vision which have led to the widespread deployment of image recognition and generation systems in socially relevant applications, from hiring to security screening. Howe…
View article: Can ChatGPT read who you are?
Can ChatGPT read who you are? Open
The interplay between artificial intelligence (AI) and psychology, particularly in personality assessment, represents an important emerging area of research. Accurate personality trait estimation is crucial not only for enhancing personali…
View article: What is Beautiful is Still Good: The Attractiveness Halo Effect in the era of Beauty Filters
What is Beautiful is Still Good: The Attractiveness Halo Effect in the era of Beauty Filters Open
The impact of cognitive biases on decision-making in the digital world remains under-explored despite its well-documented effects in physical contexts. This study addresses this gap by investigating the attractiveness halo effect using AI-…
View article: Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora
Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora Open
Large language models (LLMs) often inherit and amplify social biases embedded in their training data. A prominent social bias is gender bias. In this regard, prior work has mainly focused on gender stereotyping bias - the association of sp…
View article: What is Beautiful is Still Good: The Attractiveness Halo Effect in the era of Beauty Filters
What is Beautiful is Still Good: The Attractiveness Halo Effect in the era of Beauty Filters Open
The impact of cognitive biases on decision-making in the digital world remains under-explored despite its well-documented effects in physical contexts. This study addresses this gap by investigating the attractiveness halo effect using AI-…
View article: Exposed or Erased: Algorithmic Censorship of Nudity in Art
Exposed or Erased: Algorithmic Censorship of Nudity in Art Open
The intersection between art and technology poses new challenges for creative expression in the digital space. This paper investigates the algorithmic censorship of artistic nudity in social platforms by means of a qualitative study via se…
View article: Mirror, Mirror on the Wall, Who Is the <i>Whitest</i> of All? Racial Biases in Social Media Beauty Filters
Mirror, Mirror on the Wall, Who Is the <i>Whitest</i> of All? Racial Biases in Social Media Beauty Filters Open
Digital beauty filters are pervasive in social media platforms. Despite their popularity and relevance in the selfies culture, there is little research on their characteristics and potential biases. In this article, we study the existence …
View article: Unconventional data, unprecedented insights: leveraging non-traditional data during a pandemic
Unconventional data, unprecedented insights: leveraging non-traditional data during a pandemic Open
Introduction The COVID-19 pandemic prompted new interest in non-traditional data sources to inform response efforts and mitigate knowledge gaps. While non-traditional data offers some advantages over traditional data, it also raises concer…
View article: Can ChatGPT Read Who You Are?
Can ChatGPT Read Who You Are? Open
The interplay between artificial intelligence (AI) and psychology, particularly in personality assessment, represents an important emerging area of research. Accurate personality trait estimation is crucial not only for enhancing personali…
View article: Predicting COVID-19 pandemic waves including vaccination data with deep learning
Predicting COVID-19 pandemic waves including vaccination data with deep learning Open
Introduction During the recent COVID-19 pandemics, many models were developed to predict the number of new infections. After almost a year, models had also the challenge to include information about the waning effect of vaccines and by inf…
View article: Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated Learning
Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated Learning Open
Federated Learning (FL) has been proposed as a privacy-preserving solution for distributed machine learning, particularly in heterogeneous FL settings where clients have varying computational capabilities and thus train models with differe…
View article: Structural Group Unfairness: Measurement and Mitigation by means of the Effective Resistance
Structural Group Unfairness: Measurement and Mitigation by means of the Effective Resistance Open
Social networks contribute to the distribution of social capital, defined as the relationships, norms of trust and reciprocity within a community or society that facilitate cooperation and collective action. Therefore, better positioned me…
View article: Towards Algorithmic Fairness by means of Instance-level Data Re-weighting based on Shapley Values
Towards Algorithmic Fairness by means of Instance-level Data Re-weighting based on Shapley Values Open
Algorithmic fairness is of utmost societal importance, yet state-of-the-art large-scale machine learning models require training with massive datasets that are frequently biased. In this context, pre-processing methods that focus on modeli…