4 papers
Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
Haozheng Luo, Yimin Wang, Jiahao Yu +2
We propose CRAFT, a red-teaming alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness against jailbreak attacks. Unlike p…
POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models
Yangguang Shao, Xinjie Lin, Haozheng Luo +4
Large language models (LLMs) have achieved remarkable success in various domains, primarily due to their strong capabilities in reasoning and generating human-like text. Despite th…
GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models
Haozheng Luo, Chenghao Qiu, Yimin Wang +9
We propose the first unified adversarial attack benchmark for Genomic Foundation Models (GFMs), named GenoArmory. Unlike existing GFM benchmarks, GenoArmory offers the first compre…
Decoupled Alignment for Robust Plug-and-Play Adaptation
Haozheng Luo, Jiahao Yu, Wenxin Zhang +9
We introduce a training-free safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning or reinforcement learning from human fe…