Large language models (LLMs) have demonstrated impressive performance in text generation tasks; however, their embedding spaces often suffer from the isotropy problem, resulting in poor discrimination of domain-specific terminology, particularly in legal and financial contexts. This weakness in term-level representation can severely hinder downstream tasks such as legal judgment prediction or financial risk analysis, where subtle semantic distinctions are critical. To address this problem, we propose TermGPT, a multi-level contrastive fine-tuning framework designed for terminology adaptation. We first construct a sentence graph to capture semantic and structural relations, and generate semantically consistent yet discriminative positive and negative samples based on contextual and topological cues. We then devise a multi-level contrastive learning approach at both the sentence and token levels, enhancing global contextual understanding and fine-grained term discrimination. To support robust evaluation, we construct the first financial terminology dataset derived from official regulatory documents. Experiments show that TermGPT outperforms existing baselines in term discrimination tasks within the finance and legal domains.

Reinforcement learning-based recommendation systems (RLRS) are increasingly favored for their ability to leverage online interactive feedback, enabling adaptive and personalized decision-making. In this setting, user feedback serves as both a behavioral signal and an optimization target, making it essential for policy learning. However, collecting such feedback, e.g., clicks, ratings, and engagement traces, raises serious privacy concerns, posing critical challenges for value estimation, online adaptation, and privacy protection. In this paper, we propose FeedGuard, a critic-guided reinforcement learning framework with privacy-preserving feedback. FeedGuard enhances trajectory modeling via critic guidance, enables joint online fine-tuning with effective exploration–exploitation tradeoffs, and enforces end-to-end privacy protection across the feedback lifecycle via split federated learning and differential privacy. We further provide a formal analysis of its differential privacy guarantees. Extensive experiments on four public recommendation datasets and the VirtualTB platform show that FeedGuard performs well in both offline and online settings, while maintaining rigorous privacy guarantees with minimal degradation.

Constructive Interference (CI) has shown great advantages in improving security and reliability of communication systems, which utilizes channel state information (CSI) and knowledge of the instantaneous information data on symbol level. In this paper, we explore the CI-based secure precoding problem under a dual-hop and half-duplex downlink transmission relay system in the presence of an eavesdropper. We propose to jointly optimize the precoding strategy at the source and at the relay through an alternating optimization process. To alleviate the high computational costs and circumvent the difficulty of practical implementation, we propose a low-complexity iterative algorithm for the optimization, where we use Karush-Kuhn-Tucker (KKT) conditions to analyze and simplify the previous optimization problem at the relay. Numerical results show that the proposed algorithm can achieve an improved performance compared with traditional zero-forcing/regularized zero-forcing (ZF/RZF) methods and significantly degrade the eavesdropper’s performance.