Individualization of language models and language moderation

Researcher: Judith Sieker
Publications: Judith Sieker, Oliver Bott, Torgrim Solstad, Sina Zarrieß (2023): Beyond the Bias: Unveiling the Quality of Implicit Causality Prompt Continuations in Language Models Full Publication

Judith Sieker, Sina Zarrieß (2023): When Your Language Model Cannot Even Do Determiners Right: Probing for Anti-Presuppositions and the Maximize Presupposition! Principle Full Publication

Özge Alaçam, Ronja Utescher, Hannes Grönner, Judith Sieker, Sina Zarrieß (2024): WikiScenes with Descriptions: Aligning Paragraphs and Sentences with Images in Wikipedia Articles Full Publication

Judith Sieker, Simeon Junker, Ronja Utescher, Nazia Attari, Heiko Wersing, Hendrik Buschmeier, Sina Zarrieß (2024): The Illusion of Competence: Evaluating the Effect of Explanations on Users’ Mental Models of Visual Question Answering Systems Full Publication
Collaboration: David Schmidt, Lina Mavrina
Research Theme: R1 Human agency
Tags: 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.