5 papers
Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent Systems
Yiyang Zhao, Zhuo Zhang, Qingxuan Le +2
The rapid evolution of Large Language Models (LLMs) from passive assistants to autonomous, execution-capable agents has introduced critical operational risks. Most current evaluati…
CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning
Zhuo Wang, Zhuo Zhang, Yafu Li +3
Large Language Models (LLMs) exhibit strong mathematical reasoning when trained on high-quality Chain-of-Thought (CoT) that articulates intermediate steps, yet costly CoT curation…
SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC
Jinglong Luo, Zhuo Zhang, Yehong Zhang +6
Large Language Models (LLMs) have revolutionized numerous fields, yet their adaptation to specialized tasks in privacy-sensitive domains such as healthcare and finance remains cons…
Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models
Yingqi Hu, Zhuo Zhang, Jingyuan Zhang +4
Federated large language models (FedLLMs) enable cross-silo collaborative training among institutions while preserving data locality, making them appealing for privacy-sensitive do…
SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC
Jinglong Luo, Yehong Zhang, Zhuo Zhang +5
With the growing use of Transformer models hosted on cloud platforms to offer inference services, privacy concerns are escalating, especially concerning sensitive data like investm…