Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models
Zirui He, Haiyan Zhao, Yiran Qiao +4
The ability of large language models (LLMs) to follow instructions is crucial for their practical applications, yet the underlying mechanisms remain poorly understood. This paper p…
cs.LG2024
Certified Causal Defense with Generalizable Robustness
Yiran Qiao, Yu Yin, Chen Chen +1
While machine learning models have proven effective across various scenarios, it is widely acknowledged that many models are vulnerable to adversarial attacks. Recently, there have…