Context-Aware Hierarchical Learning: A Two-Step Paradigm towards Safer LLMs

Tengyun Ma (Great Bay University) · Damon Yao (Harbin Institute of Technology) · Daojing He (Harbin Institute of Technology) · Shihao Peng (Wuhan University) · YU LI (Zhejiang University) · Shaohui Liu (Harbin Institute of Technology) · Zhuotao Tian (The Chinese University of Hong Kong)

attack success ratescontext-aware hierarchical learningcontextual correlationsconventional attacksfunction-calling mechanismsinstruction hierarchyllm robustnessmodel behaviorrole-specific instruction constraintssecurity assessment frameworksemantic comprehensiontool-completion attacktool-completion benchmarkzero-shot evaluations

Large Language Models (LLMs) have emerged as powerful tools for diverse applications. However, their uniform token processing paradigm introduces critical vulnerabilities in instruction handling, particularly when exposed to adversarial scenarios. In this work, we identify and propose a novel class of vulnerabilities, termed Tool-Completion Attack (TCA), which exploits function-calling mechanisms to subvert model behavior. To evaluate LLM robustness against such threats, we introduce the Tool-Completion benchmark, a comprehensive security assessment framework, which reveals that even state-of-the-art models remain susceptible to TCA, with surprisingly high attack success rates. To address these vulnerabilities, we introduce Context-Aware Hierarchical Learning (CAHL), a sophisticated mechanism that dynamically equilibrates semantic comprehension with role-specific instruction constraints. CAHL leverages the contextual correlations between different instruction segments to establish a robust, context-aware instruction hierarchy. Extensive experiments demonstrate that CAHL significantly enhances LLM robustness against both conventional attacks and the proposed TCA, exhibiting strong generalization capabilities in zero-shot evaluations while still preserving model performance on generic tasks. Our code is available at https://github.com/S2AILab/CAHL.