Individualization of language models and language moderation

Judith Sieker
David Schmidt, Lina Mavrina
Research Theme
R1 Human agency
Linguistics LLMs

My research involves understanding and improving the linguistic knowledge captured in (large) language models, focusing particularly on the level of semantics and discourse processing. I aim to deepen my understanding through the utilization of linguistic test suites, improve evaluation methodologies for assessing language models’ linguistic proficiency, and investigate ways to adapt language models to individual users’ needs, considering diverse speaker groups and domains.