ZZZhuo Zhang

Zhuo Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zhuo Zhang has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent Systems

    by Yiyang Zhao, Zhuo Zhang, Qingxuan Le, Lizhen Qu, Zenglin Xu

    The rapid evolution of Large Language Models (LLMs) from passive assistants to autonomous, execution-capable agents has introduced critical operational risks. Most current evaluation frameworks neglect procedural compliance, leading to ''Machiavellian'' behaviors where agents strategically violate safety rules to maximize rewards—a direct manifestation of Goodhart's Law. To address this blind spot, we introduce MAC-Bench, a dynamic, adversarial benchmark designed to evaluate the procedural alignment of multi-agent systems under realistic pressure. We propose the SERV (Seed \rightarrow Evolve \rightarrow Refine \rightarrow Verify) pipeline, an ''Agent-as-a-Benchmark'' paradigm that transforms unstructured legal texts into executable, contamination-free scenarios. By synthesizing holographic sandbox environments and injecting calibrated social-engineering pressure vectors, MAC-Bench forces agents into Pareto-optimal trade-offs between task success and regulatory adherence. We introduced novel metrics: the Compliance-Weighted Success Rate (CSR) and the Machiavellian Gap (MG), and conducted a comprehensive evaluation of state-of-the-art frontier models to reveal the pervasive trade-offs between success and compliance.

  • Open Access

    PPFedIT: Towards Privacy-Preserving Federated Instruction Tuning with Few-shot Local Examples

    by Zhuo Zhang, Jingyuan Zhang, Jintao Huang, Hui Wang, Yue Yu, Hongzhi Zhang, Xun Zhou, Lizhen Qu, Zenglin Xu

    Instruction tuning has been identified as a crucial technique for optimizing large language models (LLMs) to generate human-aligned responses. Nonetheless, gathering diversified and superior-quality instruction data for such tuning presents notable obstacles, especially in privacy-sensitive domains. Federated instruction tuning ( FedIT ) has emerged as a promising solution by consolidating collaborative training across multiple data owners, resulting in a privacy-enhancing learning model. Existing FedIT studies assume that clients have sufficient training data, however, in reality, many clients only have few-shot samples, leading to either overfitting in federated LLM or degraded performance. At the same time, this federated few-shot environment also increases the risk of training data extraction attacks, as the LLM may well memorize the limited training data. To address these issues, this paper proposes a novel federated algorithm, PPFedIT , designed to enhance privacy protection and model performance of federated few-shot learning. PPFedIT comprises three vital steps on the client side: (1) synthetic data generation, which utilizes the strong generation capacity of LLMs to generate synthetic data, aiming to diversify and enrich local data; (2) parameter isolation training, which respectively updates the parameters of a shared global LLM on the synthetic data and the parameters of local LLMs on the local data, consequently mitigating the noise impact of the synthetic data; (3) local aggregation then sharing mechanism, which mixes the parameters of the global LLM and those of a local LLM first, before uploading them to a server for aggregation. This effectively mitigates data extraction attacks. Extensive experiments on three open-source datasets demonstrate PPFedIT significantly enhances model performance (averaging 8.4%) and reduces the risk of data extraction attacks (approximately 20%) in practical and challenging federated few-shot scenarios.

  • Open Access

    Empowering Large Language Model Agent through Step-Level Self-Critique and Self-Training

    by Yuanzhao Zhai, Huanxi Liu, Zhuo Zhang, Tong Lin, Kele Xu, Cheng Yang, Dawei Feng, Bo Ding, Huaimin Wang


  • Open Access

    Preference-Strength-Aware Self-Improving Alignment with Generative Preference Models

    by Yuanzhao Zhai, Zhuo Zhang, Cheng Yang, Kele Xu, Yue Yu, Wei Li, Hui Wang, Zenglin Xu, Dawei Feng, Bo Ding, et al.

  • Open Access

    FedHLT: Efficient Federated Low-Rank Adaption with Hierarchical Language Tree for Multilingual Modeling

    by Zhihan Guo, Yifei Zhang, Zhuo Zhang, Zenglin Xu, Irwin King

    Federated Multilingual Modeling (FMM) has become an essential approach in natural language processing (NLP) due to increasing linguistic diversity and the heightened emphasis on data privacy. However, FMM faces two primary challenges: 1) the high communication costs inherent in network operations, and 2) the complexities arising from parameter interference, as languages exhibit both unique characteristics and shared features. To tackle these issues, we introduce a communication-efficient framework for Multilingual Modeling (MM) that combines low-rank adaptation with a hierarchical language tree structure. Our method maintains the base model's weights while focusing on updating only the Low-rank adaptation (LoRA) parameters, significantly reducing communication costs. Additionally, we mitigate parameter conflicts by organizing languages based on their familial ties rather than merging all LoRA parameters together. Our experimental findings reveal that this novel model surpasses established baseline models in performance and markedly decreases communication overhead.