3 papers
cs.CL2024
Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
Zhanhui Zhou, Zhixuan Liu, Jie Liu +3
Large language models are usually fine-tuned to align with human preferences. However, fine-tuning a large language model can be challenging. In this work, we introduce $\textit{we…
cs.LG2024
Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization
Zhanhui Zhou, Jie Liu, Jing Shao +4
A single language model, even when aligned with labelers through reinforcement learning from human feedback (RLHF), may not suit all human preferences. Recent approaches therefore…
cs.CL2024
Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!
Zhanhui Zhou, Jie Liu, Zhichen Dong +4
Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans. However, this paper introduces a training-free attack method capable of reversing sa…