activity
20232026
collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

SENSESHIFT: Continuous Sentiment-Controlled Text Generation via Encoder-based Mask Infilling

Shahed Masoudian, Markus Frohmann, Emmanouil Karystinaios +2

Recent controllable text generation (CTG) for sentiment control has largely focused on decoder-based large language models, making causal attention the dominant paradigm. While eff…

cs.CL2025

Double Entendre: Robust Audio-Based AI-Generated Lyrics Detection via Multi-View Fusion

Markus Frohmann, Gabriel Meseguer-Brocal, Markus Schedl +1

The rapid advancement of AI-based music generation tools is revolutionizing the music industry but also posing challenges to artists, copyright holders, and providers alike. This n…

cs.CL2024

Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization

Shahed Masoudian, Markus Frohmann, Navid Rekabsaz +1

Language models frequently inherit societal biases from their training data. Numerous techniques have been proposed to mitigate these biases during both the pre-training and fine-t…

cs.CL20242 cited

Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation

Markus Frohmann, Igor Sterner, Ivan Vulić +2

Segmenting text into sentences plays an early and crucial role in many NLP systems. This is commonly achieved by using rule-based or statistical methods relying on lexical features…

cs.CL2024

Synthetic Lyrics Detection Across Languages and Genres

Yanis Labrak, Markus Frohmann, Gabriel Meseguer-Brocal +1

In recent years, the use of large language models (LLMs) to generate music content, particularly lyrics, has gained in popularity. These advances provide valuable tools for artists…

cs.CL2024

What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition

Carolin Holtermann, Markus Frohmann, Navid Rekabsaz +1

The knowledge encapsulated in a model is the core factor determining its final performance on downstream tasks. Much research in NLP has focused on efficient methods for storing an…