Pepa's P1 Publications
Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework
Jingyi Sun, Pepa Atanasova, Isabelle Augenstein
Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods
Haeun Yu, Pepa Atanasova, Isabelle Augenstein
DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models
Sara V. Marjanović, Haeun Yu, Pepa Atanasova, Maria Maistro, Christina Lioma, Isabelle Augenstein
Faithfulness Tests for Natural Language Explanations
Pepa Atanasova, Oana-Maria Camburu, Christina Lioma, Thomas Lukasiewicz, Jakob G. Simonsen, Isabelle Augenstein
Explaining Interactions Between Text Spans
Sagnik R. Choudhury, Pepa Atanasova, Isabelle Augenstein