MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability

1 code implementation • 23 May 2024 • Yanrui Du, Sendong Zhao, Danyang Zhao, Ming Ma, Yuhan Chen, Liangyu Huo, Qing Yang, Dongliang Xu, Bing Qin

When encountering malicious instructions, the router will assign a higher weight to the safe LLM to ensure that responses are harmless.

Don't Ignore Dual Logic Ability of LLMs while Privatizing: A Data-Intensive Analysis in Medical Domain

1 code implementation • 8 Sep 2023 • Yanrui Du, Sendong Zhao, MuZhen Cai, Ming Ma, Danyang Zhao, Jiawei Cao, Bing Qin

We conduct several experiments to analyze the dual logic ability of LLMs by examining the consistency of the stance in responses to paired questions about the same fact.

Fact Checking Knowledge Graphs