Zishuai Zhang

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, namely factually incorrect or unfaithful outputs, poses a critical obstacle to their deployment in high-stakes applications. Although recent hallucination detection methods have made encouraging progress, they typically rely on costly output-level consistency checks or static hidden-state probes that capture shallow dataset-specific patterns, leading to substantial degradation under cross-dataset evaluation. In this work, we propose AURORA, a novel hallucination detection framework that shifts the focus from static representations to the weight-gradient dynamics of LLMs. Our key insight is that hallucinated and faithful answers induce qualitatively different gradient update patterns on the model's parameters. Specifically, hallucinated samples trigger asymmetric and structurally misaligned gradients, which can be captured through two complementary features: (1) the skewness of the cosine similarity distribution between weight matrices and their gradient update directions, and (2) the rotation ratio, which quantifies how much the gradient update reorients the singular-vector basis of weight matrices via SVD. AURORA achieves strong hallucination detection performance across four model families and four benchmark datasets. Further analyses demonstrate that our method scales effectively across model sizes and transfers to out-of-domain tasks, including mathematical reasoning and vision-language scenarios.

Zishuai Zhang, Hainan zhang, Weihua Li et al.

Private data holds promise for improving LLMs due to its high quality, but its scattered distribution across data silos and the high computational demands of LLMs limit their deployment in federated environments. To address this, the transformer-based federated split models are proposed, which offload most model parameters to the server (or distributed clients) while retaining only a small portion on the client to ensure data privacy. Despite this design, they still face three challenges: 1) Peer-to-peer key encryption struggles to secure transmitted vectors effectively; 2) The auto-regressive nature of LLMs means that federated split learning can only train and infer sequentially, causing high communication overhead; 3) Fixed partition points lack adaptability to downstream tasks. In this paper, we introduce FedSEA-LLaMA, a Secure, Efficient, and Adaptive Federated splitting framework based on LLaMA2. First, we inject Gaussian noise into forward-pass hidden states to enable secure end-to-end vector transmission. Second, we employ attention-mask compression and KV cache collaboration to reduce communication costs, accelerating training and inference. Third, we allow users to dynamically adjust the partition points for input/output blocks based on specific task requirements. Experiments on natural language understanding, summarization, and conversational QA tasks show that FedSEA-LLaMA maintains performance comparable to centralized LLaMA2 and achieves up to 8x speedups in training and inference. Further analysis of privacy attacks and different partition points also demonstrates the effectiveness of FedSEA-LLaMA in security and adaptability.