4 papers
Backdooring Bias in Large Language Models
Anudeep Das, Prach Chantasantitam, Gurjot Singh +3
Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used…
Understanding and Preserving Safety in Fine-Tuned LLMs
Jiawen Zhang, Yangfan Hu, Kejia Chen +7
Fine-tuning is an essential and pervasive functionality for applying large language models (LLMs) to downstream tasks. However, it has the potential to substantially degrade safety…
Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance
Jiawen Zhang, Lipeng He, Kejia Chen +4
Fine-tuning safety-aligned large language models (LLMs) can substantially compromise their safety. Previous approaches require many safety samples or calibration sets, which not on…
StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs
Jialin Yang, Dongfu Jiang, Lipeng He +17
As Large Language Models (LLMs) become integral to software development workflows, their ability to generate structured outputs has become critically important. We introduce Struct…