3 papers
cs.CL2025
EcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generation
Ruobing Yao, Yifei Zhang, Shuang Song +2
Retrieval-Augmented Generation (RAG) compensates for the static knowledge limitations of Large Language Models (LLMs) by integrating external knowledge, producing responses with en…
cs.LG2025
Differential Privacy Personalized Federated Learning Based on Dynamically Sparsified Client Updates
Chuanyin Wang, Yifei Zhang, Neng Gao +1
Personalized federated learning is extensively utilized in scenarios characterized by data heterogeneity, facilitating more efficient and automated local training on data-owning te…
cs.CL2025
ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generation
Ruobing Yao, Yifei Zhang, Shuang Song +3
While Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by incorporating external knowledge, they still face persistent challenges in retrieval inef…