[2603.02219] NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels

Computer Science > Machine Learning arXiv:2603.02219 (cs) [Submitted on 10 Feb 2026] Title:NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels Authors:Junfeng Fang, Nachuan Chen, Houcheng Jiang, Dan Zhang, Fei Shen, Xiang Wang, Xiangnan He, Tat-Seng Chua View a PDF of the paper titled NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels, by Junfeng Fang and 7 other authors View PDF HTML (experimental) Abstract:Large language models are increasingly deployed in streaming scenarios, rendering conventional post-hoc safeguards ineffective as they fail to interdict unsafe content in real-time. While streaming safeguards based on token-level supervised training could address this, they necessitate expensive annotations and suffer from severe overfitting. In this work, we challenge the paradigm that streaming safety must rely on token-level supervised training. Instead, it is an inherent capability of well-trained post-hoc safeguards, as they already encode token-level risk signals in hidden representations. Hence, we introduce NExT-Guard, a training-free framework that achieves streaming safeguards by monitoring interpretable latent features from Sparse Autoencoders (SAEs). It uses pretrained SAEs from publicly available base LLMs, enabling flexible, low-cost deployment without token-level supervision. Experimental results show that NExT-Guard outperforms both post-hoc and streaming safeguards based on supervised training, with superior r...