2 papers
cs.CL2026
Enhancing Safety of Large Language Models via Embedding Space Separation
Xu Zhao, Xiting Wang, Weiran Shen
Large language models (LLMs) have achieved impressive capabilities, yet ensuring their safety against harmful prompts remains a critical challenge. Recent work has revealed that th…
cs.IR2026
Enhancing Long-Term Welfare in Recommender Systems: An Information Revelation Approach
Xu Zhao, Xiaopeng Ye, Chen Xu +2
Improving the long-term user welfare (e.g., sustained user engagement) has become a central objective of recommender systems (RS). In real-world platforms, the creation behaviors o…