Modern Large language models (LLMs) can still generate responses that may not
be aligned with human expectations or values. While many weight-based alignment
methods have been proposed, many of them still leave models vulnerable to
attacks when used on their own. To help mitigate this issue, we introduce
Bergeron, a framework designed to improve the robustness of LLMs against
adversarial attacks. Bergeron employs a two-tiered architecture. Here, a
secondary LLM serves as a simulated conscience that safeguards a primary LLM.
We do this by monitoring for and correcting potentially harmful text within
both the prompt inputs and the generated outputs of the primary LLM. Empirical
evaluation shows that Bergeron can improve the alignment and robustness of
several popular LLMs without costly fine-tuning. It aids both open-source and
black-box LLMs by complementing and reinforcing their existing alignment
training.

通过引入 Bergeron 框架，我们可以增强大型语言模型对抗攻击的能力，改善模型的对齐性和稳健性，而无需昂贵的微调，从而为开源和黑箱语言模型提供辅助和加强对现有对齐训练的效果。