Related papers: Making Hidden Bias Visible: Designing a Feedback E…

Medical images often contain multiple labels with imbalanced distributions and co-occurrence, leading to bias in multi-label medical image classification. Close collaboration between medical professionals and machine learning practitioners…

One of the continuing challenges of Human Computer Interaction research is the full inclusion of people with special needs into the digital world. In particular, this crucial category includes people that experiences some kind of limitation…

Mixed-initiative visual analytics systems incorporate well-established design principles that improve users' abilities to solve problems. As these systems consider whether to take initiative towards achieving user goals, many current…

Large Language Models (LLMs) have emerged as powerful candidates to inform clinical decision-making processes. While these models play an increasingly prominent role in shaping the digital landscape, two growing concerns emerge in…

The increasing reliance on digital information necessitates advancements in conversational search systems, particularly in terms of information transparency. While prior research in conversational information-seeking has concentrated on…

What we discover and see online, and consequently our opinions and decisions, are becoming increasingly affected by automated machine learned predictions. Similarly, the predictive accuracy of learning machines heavily depends on the…

Cognitive biases have been studied in psychology, sociology, and behavioral economics for decades. Traditionally, they have been considered a negative human trait that leads to inferior decision-making, reinforcement of stereotypes, or can…

Much attention and concern has been raised recently about bias and the use of machine learning algorithms in healthcare, especially as it relates to perpetuating racial discrimination and health disparities. Following an initial system…

Designing digital artifacts is not a linear, straightforward process. This is particularly true when applying a user-centered design approach, or co-design, with users who are unable to participate in the design process. Although the…

It is evident that deep text classification models trained on human data could be biased. In particular, they produce biased outcomes for texts that explicitly include identity terms of certain demographic groups. We refer to this type of…

Large language models offer transformative potential for healthcare, yet their responsible and equitable development depends critically on a deeper understanding of how training data characteristics influence model behavior, including the…

Dementia care requires healthcare professionals to balance a patient's medical needs with a deep understanding of their personal needs, preferences, and emotional cues. However, current digital tools prioritise quantitative metrics over…

Algorithms and technologies are essential tools that pervade all aspects of our daily lives. In the last decades, health care research benefited from new computer-based recruiting methods, the use of federated architectures for data…

Prior research on exposure fairness in the context of recommender systems has focused mostly on disparities in the exposure of individual or groups of items to individual users of the system. The problem of how individual or groups of items…

In an ideal world, deployed machine learning models will enhance our society. We hope that those models will provide unbiased and ethical decisions that will benefit everyone. However, this is not always the case; issues arise during the…

Through exposing items to users, implicit feedback recommender systems influence the logged interactions, and, ultimately, their own recommendations. This effect is called exposure bias and it can lead to issues such as filter bubbles and…

Combining simple elements from the literature, we define a linear model that is geared toward sparse data, in particular implicit feedback data for recommender systems. We show that its training objective has a closed-form solution, and…

Debiasing methods in NLP models traditionally focus on isolating information related to a sensitive attribute (e.g., gender or race). We instead argue that a favorable debiasing method should use sensitive information 'fairly,' with…

While personalized recommendations are often desired by users, it can be difficult in practice to distinguish cases of bias from cases of personalization: we find that models generate racially stereotypical recommendations regardless of…

Existing benchmarks evaluating biases in large language models (LLMs) primarily rely on explicit cues, declaring protected attributes like religion, race, gender by name. However, real-world interactions often contain implicit biases,…