Teaching

Explaining and Evaluating Bilingual Natural Language Inference Questions

Extend an existing dataset to German and enrich it with additional explanation scoring.

Explanation Quality Assessment

Conducting human evaluation for counterfactual examples.

When Anonymization Meets Explainability

Implementing and evaluating various XAI approaches on the anonymization task. Co-lead with Ibrahim Baroud.

Explainability for Large Language Models

Explaining Model Behavior on Long-form Methodical Tasks. Co-lead with Nils Feldhus.