通过结构化提示框架强化LLMs中以人为中心的链式推理完整性
Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework
AI总结：
本文提出结构化提示框架以提升LLMs链式推理的可靠性及安全威胁检测能力，通过16个核心维度因素优化推理过程，实验证明在DDoS攻击检测中推理能力提升达40%，并获得高人评一致性。
摘要：
链式推理（CoT）提示已被用于增强LLMs的推理能力。然而，在安全敏感的分析任务中，其可靠性仍不够充分，特别是在结构化的人类评估中。替代方法，如模型扩展和微调，可以用来提高性能，但这些方法通常成本高、计算密集或难以审计。相比之下，提示工程提供了一种轻量、透明且可控的机制来引导LLM推理。本研究提出了一种结构化提示工程框架，旨在增强CoT推理的完整性，同时提高本地LLM部署中的安全威胁和攻击检测的可靠性。该框架包含16个因素，分为四个核心维度：（1）上下文和范围控制，（2）证据接地和可追溯性，（3）推理结构和认知控制，（4）安全特定的分析约束。与启发式优化提示用语不同，该框架引入了显式的推理控制来缓解幻觉并防止推理漂移，同时在安全敏感的上下文中加强可解释性。以SDN流量中的DDoS攻击检测为例，多个模型家族在结构化和非结构化提示条件下进行了评估。帕累托前沿分析和消融实验显示推理能力的持续提升（在较小模型中可达40%）以及在不同规模下的稳定准确率提升。具有强评分者一致性（Cohen's k > 0.80）的人类评估确认了鲁棒性。结果确立了结构化提示作为可靠且实用的方法，用于可解释的AI驱动网络安全分析。
英文摘要：
Chain-of-Thought (CoT) prompting has been used to enhance the reasoning capability of LLMs. However, its reliability in security-sensitive analytical tasks remains insufficiently examined, particularly under structured human evaluation. Alternative approaches, such as model scaling and fine-tuning can be used to help improve performance. These methods are also often costly, computationally intensive, or difficult to audit. In contrast, prompt engineering provides a lightweight, transparent, and controllable mechanism for guiding LLM reasoning. This study proposes a structured prompt engineering framework designed to strengthen CoT reasoning integrity while improving security threat and attack detection reliability in local LLM deployments. The framework includes 16 factors grouped into four core dimensions: (1) Context and Scope Control, (2) Evidence Grounding and Traceability, (3) Reasoning Structure and Cognitive Control, and (4) Security-Specific Analytical Constraints. Rather than optimizing the wording of the prompt heuristically, the framework introduces explicit reasoning controls to mitigate hallucination and prevent reasoning drift, as well as strengthening interpretability in security-sensitive contexts. Using DDoS attack detection in SDN traffic as a case study, multiple model families were evaluated under structured and unstructured prompting conditions. Pareto frontier analysis and ablation experiments demonstrate consistent reasoning improvements (up to 40% in smaller models) and stable accuracy gains across scales. Human evaluation with strong inter-rater agreement (Cohen's k > 0.80) confirms robustness. The results establish structured prompting as an effective and practical approach for reliable and explainable AI-driven cybersecurity analysis.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
