I do research on Natural Language Processing under the supervision of Richard Johansson at the Data Science and AI division at Chalmers. I'm interested in language model controllability, interpretability and prediction provenance. In my research I investigate factual knowledge in language models and methods for adding knowledge to a model.
The Effect of Scaling, Retrieval Augmentation and Form on the Factual Consistency of Language Models
Lovisa Hagström, Denitsa Saynova, Tobias Norlund, Moa Johansson and Richard Johansson
EMNLP (to be published)
A Picture is Worth a Thousand Words: Natural Language Processing in Context
Lovisa Hagström
Licentiate thesis at Chalmers University of Technology
How to Adapt Pre-trained Vision-and-Language Models to a Text-only Input?
Lovisa Hagström and Richard Johansson
COLING
What do Models Learn From Training on More Than Text? Measuring Visual Commonsense Knowledge
Lovisa Hagström and Richard Johansson
ACL Student Research Workshop
Can We Use Small Models to Investigate Multimodal Fusion Methods?
Lovisa Hagström, Tobias Norlund and Richard Johansson
CLASP Conference on (Dis)embodiment
Transferring Knowledge from Vision to Language: How to Achieve it and how to Measure it?
Tobias Norlund, Lovisa Hagström and Richard Johansson
BlackboxNLP Workshop
Knowledge Distillation for Swedish NER models: A Search for Performance and Efficiency
Lovisa Hagström and Richard Johansson
Nordic Conference on Computational Linguistics (NoDaLiDa)
I supervise master's theses at Chalmers and would be happy to discuss potential thesis projects with students or organizations interested in NLP. Simply send me an email!
I also work as a teaching assistant for the courses Applied mathematical thinking, Algorithms for machine learning and inference and Applied Machine Learning at Chalmers.