6 papers
Autoregressive Models Rival Diffusion Models at ANY-ORDER Generation
Tianqi Du, Lizhe Fang, Weijie Yang +4
Diffusion language models enable any-order generation and bidirectional conditioning, offering appealing flexibility for tasks such as infilling, rewriting, and self-correction. Ho…
Decoding Large Language Diffusion Models with Foreseeing Movement
Yichuan Mo, Quan Chen, Mingjie Li +2
Large Language Diffusion Models (LLDMs) benefit from a flexible decoding mechanism that enables parallelized inference and controllable generations over autoregressive models. Yet…
Identifying and Understanding Cross-Class Features in Adversarial Training
Zeming Wei, Yiwen Guo, Yisen Wang
Adversarial training (AT) has been considered one of the most effective methods for making deep neural networks robust against adversarial attacks, while the training mechanisms an…
Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
Taiye Chen, Zeming Wei, Ang Li +1
Large Language Models (LLMs) are known to be vulnerable to jailbreaking attacks, wherein adversaries exploit carefully engineered prompts to induce harmful or unethical responses.…
Advancing LLM Safe Alignment with Safety Representation Ranking
Tianqi Du, Zeming Wei, Quan Chen +2
The rapid advancement of large language models (LLMs) has demonstrated milestone success in a variety of tasks, yet their potential for generating harmful content has raised signif…
X-Guard: Multilingual Guard Agent for Content Moderation
Bibek Upadhayay, Vahid Behzadan, Ph. D
Large Language Models (LLMs) have rapidly become integral to numerous applications in critical domains where reliability is paramount. Despite significant advances in safety framew…