3 citations · 4 across the 6 of their papers we have counts for
7 papers
Do Multilingual Large Language Models Mitigate Stereotype Bias?
Shangrui Nie, Michael Fromm, Charles Welch +7
While preliminary findings indicate that multilingual LLMs exhibit reduced bias compared to monolingual ones, a comprehensive understanding of the effect of multilingual training o…
Corpus Considerations for Annotator Modeling and Scaling
Olufunke O. Sarumi, Béla Neuendorf, Joan Plepi +3
Recent trends in natural language processing research and annotation tasks affirm a paradigm shift from the traditional reliance on a single ground truth to a focus on individual p…
Unifying Data Perspectivism and Personalization: An Application to Social Norms
Joan Plepi, Béla Neuendorf, Lucie Flek +1
Instead of using a single ground truth for language processing tasks, several recent studies have examined how to represent and predict the labels of the set of annotators. However…
Understanding Interpersonal Conflict Types and their Impact on Perception Classification
Charles Welch, Joan Plepi, Béla Neuendorf +1
Studies on interpersonal conflict have a long history and contain many suggestions for conflict typology. We use this as the basis of a novel annotation scheme and release a new da…
FACTOID: A New Dataset for Identifying Misinformation Spreaders and Political Bias
Flora Sakketou, Joan Plepi, Riccardo Cervero +3
Proactively identifying misinformation spreaders is an important step towards mitigating the impact of fake news on our society. In this paper, we introduce a new contemporary Redd…
Refining Diagnosis Paths for Medical Diagnosis based on an Augmented Knowledge Graph
Niclas Heilig, Jan Kirchhoff, Florian Stumpe +3
Medical diagnosis is the process of making a prediction of the disease a patient is likely to have, given a set of symptoms and observations. This requires extensive expert knowled…
Perceived and Intended Sarcasm Detection with Graph Attention Networks
Joan Plepi, Lucie Flek
Existing sarcasm detection systems focus on exploiting linguistic markers, context, or user-level priors. However, social studies suggest that the relationship between the author a…