Large Language Models (LLMs) have shown extraordinary capabilities in understanding
and generating text that closely mirrors human communication. However, a primary …

The rapid development of Artificial Intelligence (AI) has revolutionized numerous fields, with
large language models (LLMs) and computer vision (CV) systems driving advancements in …

Large language models (LLMs) have revolutionized language processing, but face critical
challenges with security, privacy, and generating hallucinations—coherent but factually …

Decomposing model activations into interpretable components is a key open problem in
mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for …

Recently, AI assistants based on large language models (LLMs) show surprising
performance in many tasks, such as dialogue, solving math problems, writing code, and …

Language models (LMs) have been shown to behave unexpectedly post-deployment. For
example, new jailbreaks continually arise, allowing model misuse, despite extensive red …

The rapid advancement of large language models (LLMs) has revolutionized artificial
intelligence, introducing unprecedented capabilities in natural language processing and …

To control the behavior of language models, steering methods attempt to ensure that outputs
of the model satisfy specific pre-defined properties. Adding steering vectors to the model is a …

Mechanistic interpretability aims to understand the computational mechanisms underlying
neural networks' capabilities in order to accomplish concrete scientific and engineering …

While chain-of-thought prompting (CoT) has the potential to improve the explainability of
language model reasoning, it can systematically misrepresent the factors influencing …