3 citations · 6 across the 5 of their papers we have counts for
4 papers · 1 filter
Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety
Ting Ma, Xiufeng Huang, Benlei Cui +43
As large language models are increasingly deployed in real-world systems, safety failures can still lead to harmful outputs and dangerous misuse. We argue that the essence of safet…
Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors
Weixuan Wang, Jingyuan Yang, Wei Peng
Large language models (LLMs) have achieved remarkable performance across many tasks, yet aligning them with desired behaviors remains challenging. Activation intervention has emerg…
Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs
Weixuan Wang, Barry Haddow, Minghao Wu +2
Large language models (LLMs) have revolutionized the field of natural language processing (NLP), and recent studies have aimed to understand their underlying mechanisms. However, m…
Assessing the Reliability of Large Language Model Knowledge
Weixuan Wang, Barry Haddow, Alexandra Birch +1
Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks. LLMs are typically evaluated using accuracy, yet this…