I am a third-year PhD student at the Language Technology Lab, University of Cambridge, supervised by Professor Anna Korhonen.

My research tackles multimodal and multilingual problems in Natural Language Processing, with a core interest in how we can efficiently control and adapt large models. This focus on efficiency and transfer learning began early in my NLP journey, when I contributed to AdapterHub, a well-established framework for lightweight model training.

Building on my interest in Parameter-Efficient Fine-Tuning, my current PhD work explores these ideas at the representation level. I investigate techniques like representation steering and the alignment of individually trained modules to guide model behavior without costly retraining.

Publications

ReCoVeR the Target Language: Language Steering without Sacrificing Task Performance

Hannah Sterz, Fabian David Schmidt, Goran Glavaš, and Ivan Vulić

DARE: Diverse Visual Question Answering with Robustness Evaluation

Hannah Sterz, Jonas Pfeiffer, Ivan Vulić

M2QA: Multi-domain Multilingual Question Answering

Leon Engländer, Hannah Sterz, Clifton A Poth, Jonas Pfeiffer, Ilia Kuznetsov, Iryna Gurevych

Scaling Sparse Fine-Tuning to Large Language Models

Alan Ansell, Ivan Vulić, Hannah Sterz, Anna Korhonen, Edoardo M. Ponti

Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning

Clifton Poth, Hannah Sterz, Indraneil Paul, Sukannya Purkayastha, Leon Engländer, Timo Imhof, Ivan Vulić, Sebastian Ruder, Iryna Gurevych, Jonas Pfeiffer

UKP-SQUARE: An Online Platform for Question Answering Research.

Tim Baumgärtner, Kexin Wang, Rachneet Sachdeva, Gregor Geigle, Max Eichler, Clifton Poth, Hannah Sterz, Haritz Puerto, Leonardo F. R. Ribeiro, Jonas Pfeiffer, Nils Reimers, Gözde Şahin, and Iryna Gurevych