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

Large language models (LLMs) have demonstrated impressive capabilities across diverse
languages. This study explores how LLMs handle multilingualism. Based on observed …

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

Although it is known that transformer language models (LMs) pass features from early layers
to later layers, it is not well understood how this information is represented and routed by the …

Projecting visual features into word embedding space has become a significant fusion
strategy adopted by Multimodal Large Language Models (MLLMs). However, its internal …

Advancements in LLMs have recently unveiled challenges tied to computational efficiency
and continual scalability due to their requirements of huge parameters, making the …

In recent years, multimodal large language models (MLLMs) have significantly advanced,
integrating more modalities into diverse applications. However, the lack of explainability …

Large language models (LLMs) store extensive factual knowledge, but the mechanisms
behind how they store and express this knowledge remain unclear. The Knowledge Neuron …

Sparse Autoencoders (SAEs) have emerged as a powerful unsupervised method for
extracting sparse representations from language models, yet scalable training remains a …

Text style transfer (TST) aims to modify the style of a text without altering its original
meaning. Large language models (LLMs) demonstrate superior performance across …