2 papers
cs.CR2024
A Method for Enhancing the Safety of Large Model Generation Based on Multi-dimensional Attack and Defense
Keke Zhai
Currently, large models are prone to generating harmful content when faced with complex attack instructions, significantly reducing their defensive capabilities. To address this is…
cs.CL2024
A Post-Training Enhanced Optimization Approach for Small Language Models
Keke Zhai
This paper delves into the continuous post-training optimization methods for small language models, and proposes a continuous post-training alignment data construction method for s…