12 papers
APM: Evaluating Style Personalization in LLMs with Arbitrary Preference Mappings
Philipp Spohn, Leander Girrbach, Zeynep Akata
Typical LLM responses tend to follow a default style, even though users often have distinct preferences regarding tone, verbosity, and formality that they do not explicitly state i…
Sparse Autoencoders are Topic Models
Leander Girrbach, Zeynep Akata
Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by demonstrating that they can be na…
Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas
Nils A. Herrmann, Leander Girrbach, Kirill Bykov +1
Recent work shows that large language models (LLMs) encode behavioral traits ("personas") as linear directions in activation space, often called "persona vectors". Prior work has u…
A Systematic Study of In-the-Wild Model Merging for Large Language Models
OÄuz KaÄan Hitit, Leander Girrbach, Zeynep Akata
Model merging combines multiple fine-tuned checkpoints into a single model without additional training, offering an attractive approach to reusing models and efficiently improving…
Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models
Leander Girrbach, Stephan Alaniz, Genevieve Smith +2
Vision-language models trained on large-scale multimodal datasets show strong demographic biases, but the role of training data in producing these biases remains unclear. A major b…
Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought?
Alexander von Recum, Leander Girrbach, Zeynep Akata
Reasoning LLMs (RLLMs) generate step-by-step chains of thought (CoTs) before giving an answer, which improves performance on complex tasks and makes reasoning more transparent. But…