collaborators

6 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.CL2024

SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning

Guoxin Chen, Kexin Tang, Chao Yang +3

Elucidating the reasoning process with structured explanations from question to answer is crucial, as it significantly enhances the interpretability, traceability, and trustworthin…

cs.CL2024

Inference-Time Language Model Alignment via Integrated Value Guidance

Zhixuan Liu, Zhanhui Zhou, Yuanfu Wang +2

Large language models are typically fine-tuned to align with human preferences, but tuning large models is computationally intensive and complex. In this work, we introduce $\texti…

cs.CV2024

Safety of Multimodal Large Language Models on Images and Texts

Xin Liu, Yichen Zhu, Yunshi Lan +2

Attracted by the impressive power of Multimodal Large Language Models (MLLMs), the public is increasingly utilizing them to improve the efficiency of daily work. Nonetheless, the v…

cs.CV2024

MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

Xin Liu, Yichen Zhu, Jindong Gu +3

The security concerns surrounding Large Language Models (LLMs) have been extensively explored, yet the safety of Multimodal Large Language Models (MLLMs) remains understudied. In t…

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…