Papers
arxiv:2406.07188

Merging Improves Self-Critique Against Jailbreak Attacks

Published on Jun 11
· Submitted by vicgalle on Jun 12
Authors:

Abstract

The robustness of large language models (LLMs) against adversarial manipulations, such as jailbreak attacks, remains a significant challenge. In this work, we propose an approach that enhances the self-critique capability of the LLM and further fine-tunes it over sanitized synthetic data. This is done with the addition of an external critic model that can be merged with the original, thus bolstering self-critique capabilities and improving the robustness of the LLMs response to adversarial prompts. Our results demonstrate that the combination of merging and self-critique can reduce the attack success rate of adversaries significantly, thus offering a promising defense mechanism against jailbreak attacks. Code, data and models released at https://github.com/vicgalle/merging-self-critique-jailbreaks .

Community

Sign up or log in to comment

Models citing this paper 2

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2406.07188 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2406.07188 in a Space README.md to link it from this page.

Collections including this paper 1