4 papers
Analysing the Safety Pitfalls of Steering Vectors
Yuxiao Li, Alina Fastowski, Efstratios Zaradoukas +2
Activation steering has emerged as a powerful tool to shape LLM behavior without the need for weight updates. While its inherent brittleness and unreliability are well-documented,…
Injecting Falsehoods: Adversarial Man-in-the-Middle Attacks Undermining Factual Recall in LLMs
Alina Fastowski, Bardh Prenkaj, Yuxiao Li +1
LLMs are now an integral part of information retrieval. As such, their role as question answering chatbots raises significant concerns due to their shown vulnerability to adversari…
From Confidence to Collapse in LLM Factual Robustness
Alina Fastowski, Bardh Prenkaj, Gjergji Kasneci
Ensuring the robustness of factual knowledge in LLMs is critical for reliable applications in tasks such as question answering and reasoning. However, existing evaluation methods p…
Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers
Tobias Leemann, Alina Fastowski, Felix Pfeiffer +1
We address the critical challenge of applying feature attribution methods to the transformer architecture, which dominates current applications in natural language processing and b…