1k citations · 1.3k across the 56 of their papers we have counts for
10 papers · 1 filter
SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs
Ruben Härle, Felix Friedrich, Manuel Brack +3
Large Language Models (LLMs) have demonstrated remarkable capabilities in generating human-like text, but their output may not be aligned with the user or even produce harmful cont…
LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Inconsistencies
Felix Friedrich, Simone Tedeschi, Patrick Schramowski +5
Building safe Large Language Models (LLMs) across multiple languages is essential in ensuring both safe access and linguistic diversity. To this end, we conduct a large-scale, comp…
Core Tokensets for Data-efficient Sequential Training of Transformers
Subarnaduti Paul, Manuel Brack, Patrick Schramowski +2
Deep networks are frequently tuned to novel tasks and continue learning from ongoing data streams. Such sequential training requires consolidation of new and past information, a ch…
Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
Simon Ostermann, Kevin Baum, Christoph Endres +2
Prompt injection (both direct and indirect) and jailbreaking are now recognized as significant issues for large language models (LLMs), particularly due to their potential for harm…
T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings
Björn Deiseroth, Manuel Brack, Patrick Schramowski +2
Tokenizers are crucial for encoding information in Large Language Models, but their development has recently stagnated, and they contain inherent weaknesses. Major limitations incl…
LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models
Lukas Helff, Felix Friedrich, Manuel Brack +2
This paper introduces LlavaGuard, a suite of VLM-based vision safeguards that address the critical need for reliable guardrails in the era of large-scale data and models. To this e…