6 papers
Identifying Fine-grained Forms of Populism in Political Discourse: A Case Study on Donald Trump's Presidential Campaigns
Ilias Chalkidis, Stephanie Brandl, Paris Aslanidis
Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of instruction-following tasks, yet their grasp of nuanced social science concepts remain…
A Systematic Comparison between Extractive Self-Explanations and Human Rationales in Text Classification
Stephanie Brandl, Oliver Eberle
Instruction-tuned LLMs are able to provide \textit{an} explanation about their output to users by generating self-explanations, without requiring the application of complex interpr…
Llama meets EU: Investigating the European Political Spectrum through the Lens of LLMs
Ilias Chalkidis, Stephanie Brandl
Instruction-finetuned Large Language Models inherit clear political leanings that have been shown to influence downstream task performance. We expand this line of research beyond t…
On the Interplay between Fairness and Explainability
Stephanie Brandl, Emanuele Bugliarello, Ilias Chalkidis
In order to build reliable and trustworthy NLP applications, models need to be both fair across different demographics and explainable. Usually these two objectives, fairness and e…
Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models
Laura Cabello, Emanuele Bugliarello, Stephanie Brandl +1
Pretrained machine learning models are known to perpetuate and even amplify existing biases in data, which can result in unfair outcomes that ultimately impact user experience. The…
Rather a Nurse than a Physician -- Contrastive Explanations under Investigation
Oliver Eberle, Ilias Chalkidis, Laura Cabello +1
Contrastive explanations, where one decision is explained in contrast to another, are supposed to be closer to how humans explain a decision than non-contrastive explanations, wher…