5 papers
DP-ES: Differentially Private Evolution Strategies for Prompt Optimization
Ziniu Liu, Aiping Li, Yue Han +5
Token-level differentially private (DP) prompt optimization methods such as DP-OPT can become unstable under tight privacy budgets: on GSM8K, DP-OPT obtains across…
Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning
Yue Han, Ziniu Liu
Multi-task supervised fine-tuning (SFT) often casts a heterogeneous data mixture as a single optimization problem, even though different tasks may reach their best generalization a…
Cross-Silo De-Anonymization Under Local Differential Privacy: Threat Model, Phase Transition, and Coordination Necessity
Ziniu Liu, Aiping Li
When a person's records appear in k independent data silos, each protected by (epsilon, delta)-differential privacy, standard composition yields a valid (k*epsilon, k*delta)-DP gua…
Enhancing Logical Expressiveness in Graph Neural Networks via Path-Neighbor Aggregation
Han Yu, Xiaojuan Zhao, Aiping Li +3
Graph neural networks (GNNs) can effectively model structural information of graphs, making them widely used in knowledge graph (KG) reasoning. However, existing studies on the exp…
NCV: A Node-Wise Consistency Verification Approach for Low-Cost Structured Error Localization in LLM Reasoning
Yulong Zhang, Li Wang, Wei Du +7
Verifying multi-step reasoning in large language models is difficult due to imprecise error localization and high token costs. Existing methods either assess entire reasoning chain…