21 papers
Towards Privacy-Preserving Federated Prompt Tuning under Data Heterogeneity: A Subspace-Decomposed Expert Approach
Yuhua Wang, Xiaodong Li, Yihao Guo +6
Federated prompt tuning (FPT) enables collaborative adaptation of vision--language models (VLMs) using lightweight prompts. Existing methods often address heterogeneity and privacy…
AURORA: Asymmetry and Update-Induced Rotation for Robust Hallucination Detection in Large Language Models
Zishuai Zhang, Hainan Zhang, Zhiming Zheng
Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. However, their tendency to generate hallucinations,…
Learning to Erase Private Knowledge from Multi-Documents for Retrieval-Augmented Large Language Models
Yujing Wang, Jinwen Chen, Hainan Zhang +5
Retrieval-Augmented Generation (RAG) is a promising technique for applying LLMs to proprietary domains. However, retrieved documents may contain sensitive knowledge, posing risks o…
Robust Reasoning via Dynamic Token Selection for Distribution-Aligned Self-Distillation
Ruiqi Zhang, Lingxiang Wang, Hainan Zhang Zhiming Zheng
Self-distillation improves learning efficiency by rewriting reference answers as training data that better matches the model's own distribution. However, reference answers also int…
From Unfamiliar to Familiar: Detecting Pre-training Data via Gradient Deviations in Large Language Models
Ruiqi Zhang, Lingxiang Wang, Hainan Zhang +2
Pre-training data detection for LLMs is essential for addressing copyright concerns and mitigating benchmark contamination. Existing methods mainly focus on the likelihood-based st…
Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models
Shule Lu, Yujing Wang, Hainan Zhang +5
Vision-Language Models (VLMs) have broad potential in privacy-sensitive domains such as healthcare and finance, yet strict data-sharing constraints render centralized training infe…