activity
20242026
collaborators

6 papers

cs.CL2026

Evaluating Pluralism in LLMs through Latent Perspectives

Laura Majer, Jan Å najder, Martin Tutek

The growing need to represent diverse perspectives has increased interest in pluralistic LLM generation. Although difficult to operationalize, identifying perspectives expressed in…

cs.CL2026

Context Parametrization with Compositional Adapters

Josip Jukić, Martin Tutek, Jan Šnajder

Large language models (LLMs) often seamlessly adapt to new tasks through in-context learning (ICL) or supervised fine-tuning (SFT). However, ICL is inefficient when handling many d…

cs.CL2025

Disentangling Latent Shifts of In-Context Learning with Weak Supervision

Josip Jukić, Jan Šnajder

In-context learning (ICL) enables large language models to perform few-shot learning by conditioning on labeled examples in the prompt. Despite its flexibility, ICL suffers from in…

cs.CL2025

What Makes You CLIC: Detection of Croatian Clickbait Headlines

Marija Anđelić, Dominik Šipek, Laura Majer +1

Online news outlets operate predominantly on an advertising-based revenue model, compelling journalists to create headlines that are often scandalous, intriguing, and provocative -…

cs.CL2024

LLMs for Targeted Sentiment in News Headlines: Exploring the Descriptive-Prescriptive Dilemma

Jana Juroš, Laura Majer, Jan Šnajder

News headlines often evoke sentiment by intentionally portraying entities in particular ways, making targeted sentiment analysis (TSA) of headlines a worthwhile but difficult task.…

cs.CL2024

Claim Check-Worthiness Detection: How Well do LLMs Grasp Annotation Guidelines?

Laura Majer, Jan Å najder

The increasing threat of disinformation calls for automating parts of the fact-checking pipeline. Identifying text segments requiring fact-checking is known as claim detection (CD)…