Large language models (LLMs) bring world knowledge to user preference modeling in sequential recommendation, but generation-based recommenders express next-item predictions indirectly as text. Generated outputs may fail to identify a unique candidate item, depend on candidate presentation order in the prompt, and lack...
Dao-Xuan Liu, Jia-Yi Liao, Jian-Can Wu et al.· 0 citations
This work proposes MLLMEraser, an input-aware, training-free framework for test-time unlearning that consistently outperforms state-of-the-art MLLM unlearning baselines, achieving stronger forgetting performance with lower computational cost and minimal utility degradation.
This work introduces Safin-1.5, a model built on a safety architecture and trained through recursive safety improvement, with an inference-time harness that extends its capabilities to formal reasoning, and demonstrates that Safin-1.5 achieves safety and reasoning performance, outperforming frontier models.
Jing-Nan Zheng, Cheng Jin, Ming Zhang et al.· 1 citation
Multimodal large language models (MLLMs) can reproduce sensitive, copyrighted, or unsafe information from their training data. Effective unlearning must remove target information while preserving non-target content, even within the same response. Existing methods typically apply uniform forgetting objectives to complet...
Chen-Lu Ding, Jian-Can Wu, Yan-Chen Luo et al.· 2 citations
Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move from theoretical prospect to practice, posing both challenges and opportunities for safety alignment. Models evolve through frequent updates, and their safety alignment requires continual adaptation to...
Jing-Nan Zheng, Dong-Cheng Zhang, Yi Zhang et al.· 2 citations
This work presents the first systematic safety analysis of MLRMs through large-scale empirical studies comparing MLRMs with their base MLLMs, and calls for immediate efforts to harden reasoning-augmented AI, ensuring its transformative potential aligns with ethical safeguards.
Jun-Feng Fang, Yu-Kai Wang, Rui-Peng Wang et al.· AI Plus· 1 citation
Safeguarding language model agents requires assessing complete execution trajectories under context-dependent safety policies. Existing policy-aware safeguards mainly rely on prompting or supervised fine-tuning, limiting their ability to adapt to unseen trajectories and changing policy contexts. We propose RePolicy, an...
Hou-Cheng Jiang, Bo-Xuan Zhang, Qi-Yong Zhong et al.· 0 citations
This work proposes RosePO, a framework to refine LLM-based recommendation through pairwise preference optimization with personalized smoothing, and incorporates a personalized smoothing factor predicted by a user oracle into the optimization objective.
Jia-Yi Liao, Xiang-Nan He, Ruo-Bing Xie et al.· ACM Transactions on Informat...· 0 citations
This work proposes ARMOR (Anchor Rollout and Mixed Optimization for RL), a framework that shifts the paradigm from passive penalty to active sample stabilization, enabling sustained performance improvements over extended training horizons.
Kexin Huang, Junkang Wu, Jinda Lu et al.· arXiv.org· 0 citations
Perception-Enhanced Alignment DPO (PEA-DPO), a framework for multimodal LLMs alignment, which explicitly leverages visual preference signals to overcome visual insensitivity is proposed, which demonstrates that PEA-DPO enhances sensitivity to visual context while preserving the language modeling capacity of the base mo...
Jiawei Feng, Jiancan Wu, Xingyu Zhu et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.