collaborators
Showing cs.CLShow all

9 papers · 1 filter

cs.CL2025

Weak-to-Strong Jailbreaking on Large Language Models

Xuandong Zhao, Xianjun Yang, Tianyu Pang +4

Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computati…

cs.CL2025

Bootstrapping Language Models with DPO Implicit Rewards

Changyu Chen, Zichen Liu, Chao Du +5

Human alignment in large language models (LLMs) is an active area of research. A recent groundbreaking work, direct preference optimization (DPO), has greatly simplified the proces…

cs.CL2024

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs

Xuan Zhang, Chao Du, Tianyu Pang +3

The recent development of chain-of-thought (CoT) decoding has enabled large language models (LLMs) to generate explicit logical reasoning paths for complex problem-solving. However…

cs.CL2024

Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses

Xiaosen Zheng, Tianyu Pang, Chao Du +3

Recently, Anil et al. (2024) show that many-shot (up to hundreds of) demonstrations can jailbreak state-of-the-art LLMs by exploiting their long-context capability. Nevertheless, i…

cs.CL2024

LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

Chengsong Huang, Qian Liu, Bill Yuchen Lin +3

Low-rank adaptations (LoRA) are often employed to fine-tune large language models (LLMs) for new tasks. This paper investigates LoRA composability for cross-task generalization and…

cs.CL2024

Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

Xiangming Gu, Xiaosen Zheng, Tianyu Pang +5

A multimodal large language model (MLLM) agent can receive instructions, capture images, retrieve histories from memory, and decide which tools to use. Nonetheless, red-teaming eff…