Understanding knowledge mechanisms in Large Language Models (LLMs) is crucial for
advancing towards trustworthy AGI. This paper reviews knowledge mechanism analysis …

This survey provides an in-depth analysis of knowledge conflicts for large language models
(LLMs), highlighting the complex challenges they encounter when blending contextual and …

Visual Prompting is a technique for teaching models to perform a visual task via in-context
examples, without any additional training. In this work, we analyze the activations of MAE …

Since the advent of ChatGPT, Large Language Models (LLMs) have excelled in various
tasks but remain as black-box systems. Consequently, the reasoning bottlenecks of LLMs …

Knowledge editing aims to rectify inaccuracies in large language models (LLMs) without
costly retraining for outdated or erroneous knowledge. However, current knowledge editing …

The remarkable capabilities of modern large language models are rooted in their vast
repositories of knowledge encoded within their parameters, enabling them to perceive the …

State-of-the-art language models (LMs) sometimes generate non-factual hallucinations that
misalign with world knowledge. To explore the mechanistic causes of these hallucinations …

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

Knowledge representation has been a central aim of AI since its inception. Symbolic
Knowledge Graphs (KGs) and neural Large Language Models (LLMs) can both represent …

Given the prompt" Rome is in", can we steer a language model to flip its prediction of an
incorrect token" France" to a correct token" Italy" by only multiplying a few relevant activation …