Currently, I’m a PhD student at the CopeNLU, NLP Section, University of Copenhagen. My study is advised by Prof. Isabelle Augenstein and Prof. Pepa Atanasova.

I’m interested in building and interpreting knowledge-enhanced language models.

Updates

Sep 2024 Our new work on Knowledge Conflict “DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models” is accepted to Findings of EMNLP 2024! paper

July 2024 I’m visiting UI Lab (Prof. Alice Oh) & LK Lab (Prof. Minjun Seo) at KAIST!

April 2024 I’ll present “Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods” at ACL 2024, Bangkok, Thailand. paper

Research Interests

• Explainability of Language Models: Mechanistic Interpretability
• Knowledge Intensive Language Understanding Tasks: Fact-checking, Question Answering
• Factuality: Knowledge Conflict, Parametric Knowledge Elucidation, Knowledge Editing, Machine Unlearning