Mechanistic interpretability (MI) is an emerging sub-field of interpretability that seeks to
understand a neural network model by reverse-engineering its internal computations …

Despite the ability to train capable LLMs, the methodology for maintaining their relevancy
and rectifying errors remains elusive. To this end, the past few years have witnessed a surge …

Reasoning, as an essential ability for complex problem-solving, can provide back-end
support for various real-world applications, such as medical diagnosis, negotiation, etc. This …

Abstract Language models learn a great quantity of factual information during pretraining,
and recent work localizes this information to specific model weights like mid-layer MLP …

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

Despite rapid adoption and deployment of large language models (LLMs), the internal
computations of these models remain opaque and poorly understood. In this work, we seek …

Pre-trained language models can be fine-tuned to solve diverse NLP tasks, including in few-
shot settings. Thus fine-tuning allows the model to quickly pick up task-specific" skills," but …

We report the presence of a simple neural mechanism that represents an input-output
function as a vector within autoregressive transformer language models (LMs). Using causal …

Large Language Models (LLMs) have impressive capabilities, but are also prone to
outputting falsehoods. Recent work has developed techniques for inferring whether a LLM is …

Large language models (LLMs) show inherent brittleness in their safety mechanisms, as
evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This …