Panacea: Pareto Alignment via Preference Adaptation for LLMs

no code implementations • 3 Feb 2024 • Yifan Zhong, Chengdong Ma, Xiaoyuan Zhang, Ziran Yang, Haojun Chen, Qingfu Zhang, Siyuan Qi, Yaodong Yang

Panacea trains a single model capable of adapting online and Pareto-optimally to diverse sets of preferences without the need for further tuning.

Language Modelling Large Language Model

Red Teaming Game: A Game-Theoretic Framework for Red Teaming Language Models

no code implementations • 30 Sep 2023 • Chengdong Ma, Ziran Yang, Minquan Gao, Hai Ci, Jun Gao, Xuehai Pan, Yaodong Yang

In this paper, we present Red-teaming Game (RTG), a general game-theoretic framework without manual annotation.

Language Modelling Vulnerability Detection