Skip to content
conftrace_
2024 ICML ICML 2024

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Zhuowen Yuan, Zidi Xiong, Yi Zeng, Ning Yu, Ruoxi Jia, Dawn Song, Bo Li

Topics

Artificial Intelligence > Core AI > AI Safety Machine Learning > Optimization & Theory > Bayesian Inference Artificial Intelligence > Core AI > Large Language Models

Keywords

langevin dynamics minimax optimization jailbreaking attack large language model guardrails energy-based training data augmentation
Download PDF