activity
20242026
collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

Word Class Representations Spontaneously Emerge from Successor Representations Trained on Natural Language

Mathis Immertreu, Achim Schilling, Thomas Kinfe +1

Language models are typically trained to predict the next token in a sequence. Here, we explore an alternative predictive principle from reinforcement learning: Successor Represent…

cs.CL2025

Probing Internal Representations of Multi-Word Verbs in Large Language Models

Hassane Kissane, Achim Schilling, Patrick Krauss

This study investigates the internal representations of verb-particle combinations, called multi-word verbs, within transformer-based large language models (LLMs), specifically exa…

cs.CL2025

Author-Specific Linguistic Patterns Unveiled: A Deep Learning Study on Word Class Distributions

Patrick Krauss, Achim Schilling

Deep learning methods have been increasingly applied to computational linguistics to uncover patterns in text data. This study investigates author-specific word class distributions…

cs.CL2025

Refusal Behavior in Large Language Models: A Nonlinear Perspective

Fabian Hildebrandt, Andreas Maier, Patrick Krauss +1

Refusal behavior in large language models (LLMs) enables them to decline responding to harmful, unethical, or inappropriate prompts, ensuring alignment with ethical standards. This…

cs.CL2025

Exploring Narrative Clustering in Large Language Models: A Layerwise Analysis of BERT

Awritrojit Banerjee, Achim Schilling, Patrick Krauss

This study investigates the internal mechanisms of BERT, a transformer-based large language model, with a focus on its ability to cluster narrative content and authorial style acro…

cs.CL2024

Analysis and Visualization of Linguistic Structures in Large Language Models: Neural Representations of Verb-Particle Constructions in BERT

Hassane Kissane, Achim Schilling, Patrick Krauss

This study investigates the internal representations of verb-particle combinations within transformer-based large language models (LLMs), specifically examining how these models ca…